2019-02-07 02:33:01 +09:00
|
|
|
use crate::symbol::Symbol;
|
2019-12-22 17:42:04 -05:00
|
|
|
use std::cmp;
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
|
2019-08-02 00:26:40 +03:00
|
|
|
#[cfg(test)]
|
|
|
|
mod tests;
|
|
|
|
|
2019-02-08 14:53:55 +01:00
|
|
|
/// Finds the Levenshtein distance between two strings
|
2015-12-14 22:36:31 +05:30
|
|
|
pub fn lev_distance(a: &str, b: &str) -> usize {
|
|
|
|
// cases which don't require further computation
|
|
|
|
if a.is_empty() {
|
|
|
|
return b.chars().count();
|
|
|
|
} else if b.is_empty() {
|
|
|
|
return a.chars().count();
|
|
|
|
}
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
|
2018-12-04 11:17:58 -08:00
|
|
|
let mut dcol: Vec<_> = (0..=b.len()).collect();
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
let mut t_last = 0;
|
|
|
|
|
2015-12-14 22:36:31 +05:30
|
|
|
for (i, sc) in a.chars().enumerate() {
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
let mut current = i;
|
|
|
|
dcol[0] = current + 1;
|
|
|
|
|
2015-12-14 22:36:31 +05:30
|
|
|
for (j, tc) in b.chars().enumerate() {
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
let next = dcol[j + 1];
|
|
|
|
if sc == tc {
|
|
|
|
dcol[j + 1] = current;
|
|
|
|
} else {
|
|
|
|
dcol[j + 1] = cmp::min(current, next);
|
|
|
|
dcol[j + 1] = cmp::min(dcol[j + 1], dcol[j]) + 1;
|
|
|
|
}
|
|
|
|
current = next;
|
|
|
|
t_last = j;
|
|
|
|
}
|
2018-10-29 22:39:34 +09:00
|
|
|
}
|
|
|
|
dcol[t_last + 1]
|
std: Stabilize the std::str module
This commit starts out by consolidating all `str` extension traits into one
`StrExt` trait to be included in the prelude. This means that
`UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into
one `StrExt` exported by the standard library. Some functionality is currently
duplicated with the `StrExt` present in libcore.
This commit also currently avoids any methods which require any form of pattern
to operate. These functions will be stabilized via a separate RFC.
Next, stability of methods and structures are as follows:
Stable
* from_utf8_unchecked
* CowString - after moving to std::string
* StrExt::as_bytes
* StrExt::as_ptr
* StrExt::bytes/Bytes - also made a struct instead of a typedef
* StrExt::char_indices/CharIndices - CharOffsets was renamed
* StrExt::chars/Chars
* StrExt::is_empty
* StrExt::len
* StrExt::lines/Lines
* StrExt::lines_any/LinesAny
* StrExt::slice_unchecked
* StrExt::trim
* StrExt::trim_left
* StrExt::trim_right
* StrExt::words/Words - also made a struct instead of a typedef
Unstable
* from_utf8 - the error type was changed to a `Result`, but the error type has
yet to prove itself
* from_c_str - this function will be handled by the c_str RFC
* FromStr - this trait will have an associated error type eventually
* StrExt::escape_default - needs iterators at least, unsure if it should make
the cut
* StrExt::escape_unicode - needs iterators at least, unsure if it should make
the cut
* StrExt::slice_chars - this function has yet to prove itself
* StrExt::slice_shift_char - awaiting conventions about slicing and shifting
* StrExt::graphemes/Graphemes - this functionality may only be in libunicode
* StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in
libunicode
* StrExt::width - this functionality may only be in libunicode
* StrExt::utf16_units - this functionality may only be in libunicode
* StrExt::nfd_chars - this functionality may only be in libunicode
* StrExt::nfkd_chars - this functionality may only be in libunicode
* StrExt::nfc_chars - this functionality may only be in libunicode
* StrExt::nfkc_chars - this functionality may only be in libunicode
* StrExt::is_char_boundary - naming is uncertain with container conventions
* StrExt::char_range_at - naming is uncertain with container conventions
* StrExt::char_range_at_reverse - naming is uncertain with container conventions
* StrExt::char_at - naming is uncertain with container conventions
* StrExt::char_at_reverse - naming is uncertain with container conventions
* StrVector::concat - this functionality may be replaced with iterators, but
it's not certain at this time
* StrVector::connect - as with concat, may be deprecated in favor of iterators
Deprecated
* StrAllocating and UnicodeStrPrelude have been merged into StrExit
* eq_slice - compiler implementation detail
* from_str - use the inherent parse() method
* is_utf8 - call from_utf8 instead
* replace - call the method instead
* truncate_utf16_at_nul - this is an implementation detail of windows and does
not need to be exposed.
* utf8_char_width - moved to libunicode
* utf16_items - moved to libunicode
* is_utf16 - moved to libunicode
* Utf16Items - moved to libunicode
* Utf16Item - moved to libunicode
* Utf16Encoder - moved to libunicode
* AnyLines - renamed to LinesAny and made a struct
* SendStr - use CowString<'static> instead
* str::raw - all functionality is deprecated
* StrExt::into_string - call to_string() instead
* StrExt::repeat - use iterators instead
* StrExt::char_len - use .chars().count() instead
* StrExt::is_alphanumeric - use .chars().all(..)
* StrExt::is_whitespace - use .chars().all(..)
Pending deprecation -- while slicing syntax is being worked out, these methods
are all #[unstable]
* Str - while currently used for generic programming, this trait will be
replaced with one of [], deref coercions, or a generic conversion trait.
* StrExt::slice - use slicing syntax instead
* StrExt::slice_to - use slicing syntax instead
* StrExt::slice_from - use slicing syntax instead
* StrExt::lev_distance - deprecated with no replacement
Awaiting stabilization due to patterns and/or matching
* StrExt::contains
* StrExt::contains_char
* StrExt::split
* StrExt::splitn
* StrExt::split_terminator
* StrExt::rsplitn
* StrExt::match_indices
* StrExt::split_str
* StrExt::starts_with
* StrExt::ends_with
* StrExt::trim_chars
* StrExt::trim_left_chars
* StrExt::trim_right_chars
* StrExt::find
* StrExt::rfind
* StrExt::find_str
* StrExt::subslice_offset
2014-12-10 09:02:31 -08:00
|
|
|
}
|
|
|
|
|
2019-02-08 14:53:55 +01:00
|
|
|
/// Finds the best match for a given word in the given iterator
|
2018-09-11 08:31:47 +02:00
|
|
|
///
|
2015-12-14 22:36:31 +05:30
|
|
|
/// As a loose rule to avoid the obviously incorrect suggestions, it takes
|
|
|
|
/// an optional limit for the maximum allowable edit distance, which defaults
|
2017-12-01 00:39:47 +03:00
|
|
|
/// to one-third of the given word.
|
2018-09-11 08:31:47 +02:00
|
|
|
///
|
2017-12-01 00:39:47 +03:00
|
|
|
/// Besides Levenshtein, we use case insensitive comparison to improve accuracy on an edge case with
|
|
|
|
/// a lower(upper)case letters mismatch.
|
2019-12-22 17:42:04 -05:00
|
|
|
pub fn find_best_match_for_name<'a, T>(
|
|
|
|
iter_names: T,
|
|
|
|
lookup: &str,
|
|
|
|
dist: Option<usize>,
|
|
|
|
) -> Option<Symbol>
|
|
|
|
where
|
|
|
|
T: Iterator<Item = &'a Symbol>,
|
|
|
|
{
|
2015-12-14 22:36:31 +05:30
|
|
|
let max_dist = dist.map_or_else(|| cmp::max(lookup.len(), 3) / 3, |d| d);
|
2017-12-01 00:39:47 +03:00
|
|
|
|
|
|
|
let (case_insensitive_match, levenstein_match) = iter_names
|
2019-12-22 17:42:04 -05:00
|
|
|
.filter_map(|&name| {
|
|
|
|
let dist = lev_distance(lookup, &name.as_str());
|
|
|
|
if dist <= max_dist { Some((name, dist)) } else { None }
|
|
|
|
})
|
|
|
|
// Here we are collecting the next structure:
|
|
|
|
// (case_insensitive_match, (levenstein_match, levenstein_distance))
|
|
|
|
.fold((None, None), |result, (candidate, dist)| {
|
|
|
|
(
|
|
|
|
if candidate.as_str().to_uppercase() == lookup.to_uppercase() {
|
|
|
|
Some(candidate)
|
|
|
|
} else {
|
|
|
|
result.0
|
|
|
|
},
|
|
|
|
match result.1 {
|
|
|
|
None => Some((candidate, dist)),
|
|
|
|
Some((c, d)) => Some(if dist < d { (candidate, dist) } else { (c, d) }),
|
|
|
|
},
|
|
|
|
)
|
|
|
|
});
|
2017-12-01 00:39:47 +03:00
|
|
|
|
|
|
|
if let Some(candidate) = case_insensitive_match {
|
|
|
|
Some(candidate) // exact case insensitive match has a higher priority
|
|
|
|
} else {
|
2019-10-08 01:14:42 +01:00
|
|
|
levenstein_match.map(|(candidate, _)| candidate)
|
2017-12-01 00:39:47 +03:00
|
|
|
}
|
2015-11-27 17:52:29 +01:00
|
|
|
}
|