diff options
Diffstat (limited to 'api')
| -rw-r--r-- | api/api.md | 148 | ||||
| -rw-r--r-- | api/text.md | 148 | ||||
| -rw-r--r-- | api/text.yaml | 57 |
3 files changed, 245 insertions, 108 deletions
@@ -4182,27 +4182,6 @@ for chunk in text.by_split_any(",;") say(chunk) ``` -## Text.bytes - -```tomo -Text.bytes : func(text: Text -> [Byte]) -``` - -Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text. - -Argument | Type | Description | Default ----------|------|-------------|--------- -text | `Text` | The text to be converted to UTF8 bytes. | - - -**Return:** A list of bytes (`[Byte]`) representing the text in UTF8 encoding. - - -**Example:** -```tomo ->> "Amélie".bytes() -= [65, 109, 195, 169, 108, 105, 101] - -``` ## Text.caseless_equals ```tomo @@ -4306,29 +4285,6 @@ first | `Int` | The index to begin the slice. | - = "lo" ``` -## Text.from_bytes - -```tomo -Text.from_bytes : func(bytes: [Byte] -> [Text]) -``` - -Returns text that has been constructed from the given UTF8 bytes. - -The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input. - -Argument | Type | Description | Default ----------|------|-------------|--------- -bytes | `[Byte]` | The UTF-8 bytes of the desired text. | - - -**Return:** A new text based on the input UTF8 bytes after normalization has been applied. - - -**Example:** -```tomo ->> Text.from_bytes([195, 133, 107, 101]) -= "Åke" - -``` ## Text.from_c_string ```tomo @@ -4377,10 +4333,35 @@ codepoint_names | `[Text]` | The names of each codepoint in the desired text (ca = "Åke" ``` -## Text.from_codepoints +## Text.from_utf16 + +```tomo +Text.from_utf16 : func(bytes: [Int16] -> [Text]) +``` + +Returns text that has been constructed from the given UTF16 sequence. + +The text will be normalized, so the resulting text's UTF16 sequence may not exactly match the input. + +Argument | Type | Description | Default +---------|------|-------------|--------- +bytes | `[Int16]` | The UTF-16 integers of the desired text. | - + +**Return:** A new text based on the input UTF16 sequence after normalization has been applied. + + +**Example:** +```tomo +>> Text.from_utf16([197, 107, 101]) += "Åke" +>> Text.from_utf16([12371, 12435, 12395, 12385, 12399, 19990, 30028]) += "こんにちは世界".utf16() + +``` +## Text.from_utf32 ```tomo -Text.from_codepoints : func(codepoints: [Int32] -> [Text]) +Text.from_utf32 : func(codepoints: [Int32] -> [Text]) ``` Returns text that has been constructed from the given UTF32 codepoints. @@ -4396,7 +4377,30 @@ codepoints | `[Int32]` | The UTF32 codepoints in the desired text. | - **Example:** ```tomo ->> Text.from_codepoints([197, 107, 101]) +>> Text.from_utf32([197, 107, 101]) += "Åke" + +``` +## Text.from_utf8 + +```tomo +Text.from_utf8 : func(bytes: [Byte] -> [Text]) +``` + +Returns text that has been constructed from the given UTF8 bytes. + +The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input. + +Argument | Type | Description | Default +---------|------|-------------|--------- +bytes | `[Byte]` | The UTF-8 bytes of the desired text. | - + +**Return:** A new text based on the input UTF8 bytes after normalization has been applied. + + +**Example:** +```tomo +>> Text.from_utf8([195, 133, 107, 101]) = "Åke" ``` @@ -4916,10 +4920,33 @@ language | `Text` | The ISO 639 language code for which casing rules to use. | = "İ" ``` -## Text.utf32_codepoints +## Text.utf16 ```tomo -Text.utf32_codepoints : func(text: Text -> [Int32]) +Text.utf16 : func(text: Text -> [Int16]) +``` + +Returns a list of Unicode code points for UTF16 encoding of the text. + +Argument | Type | Description | Default +---------|------|-------------|--------- +text | `Text` | The text from which to extract Unicode code points. | - + +**Return:** A list of 16-bit integer Unicode code points (`[Int16]`). + + +**Example:** +```tomo +>> "Åke".utf16() += [197, 107, 101] +>> "こんにちは世界".utf16() += [12371, 12435, 12395, 12385, 12399, 19990, 30028] + +``` +## Text.utf32 + +```tomo +Text.utf32 : func(text: Text -> [Int32]) ``` Returns a list of Unicode code points for UTF32 encoding of the text. @@ -4933,10 +4960,31 @@ text | `Text` | The text from which to extract Unicode code points. | - **Example:** ```tomo ->> "Amélie".utf32_codepoints() +>> "Amélie".utf32() = [65, 109, 233, 108, 105, 101] ``` +## Text.utf8 + +```tomo +Text.utf8 : func(text: Text -> [Byte]) +``` + +Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text. + +Argument | Type | Description | Default +---------|------|-------------|--------- +text | `Text` | The text to be converted to UTF8 bytes. | - + +**Return:** A list of bytes (`[Byte]`) representing the text in UTF8 encoding. + + +**Example:** +```tomo +>> "Amélie".utf8() += [65, 109, 195, 169, 108, 105, 101] + +``` ## Text.width ```tomo diff --git a/api/text.md b/api/text.md index bdff6841..0d50ee24 100644 --- a/api/text.md +++ b/api/text.md @@ -130,27 +130,6 @@ for chunk in text.by_split_any(",;") say(chunk) ``` -## Text.bytes - -```tomo -Text.bytes : func(text: Text -> [Byte]) -``` - -Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text. - -Argument | Type | Description | Default ----------|------|-------------|--------- -text | `Text` | The text to be converted to UTF8 bytes. | - - -**Return:** A list of bytes (`[Byte]`) representing the text in UTF8 encoding. - - -**Example:** -```tomo ->> "Amélie".bytes() -= [65, 109, 195, 169, 108, 105, 101] - -``` ## Text.caseless_equals ```tomo @@ -254,29 +233,6 @@ first | `Int` | The index to begin the slice. | - = "lo" ``` -## Text.from_bytes - -```tomo -Text.from_bytes : func(bytes: [Byte] -> [Text]) -``` - -Returns text that has been constructed from the given UTF8 bytes. - -The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input. - -Argument | Type | Description | Default ----------|------|-------------|--------- -bytes | `[Byte]` | The UTF-8 bytes of the desired text. | - - -**Return:** A new text based on the input UTF8 bytes after normalization has been applied. - - -**Example:** -```tomo ->> Text.from_bytes([195, 133, 107, 101]) -= "Åke" - -``` ## Text.from_c_string ```tomo @@ -325,10 +281,35 @@ codepoint_names | `[Text]` | The names of each codepoint in the desired text (ca = "Åke" ``` -## Text.from_codepoints +## Text.from_utf16 + +```tomo +Text.from_utf16 : func(bytes: [Int16] -> [Text]) +``` + +Returns text that has been constructed from the given UTF16 sequence. + +The text will be normalized, so the resulting text's UTF16 sequence may not exactly match the input. + +Argument | Type | Description | Default +---------|------|-------------|--------- +bytes | `[Int16]` | The UTF-16 integers of the desired text. | - + +**Return:** A new text based on the input UTF16 sequence after normalization has been applied. + + +**Example:** +```tomo +>> Text.from_utf16([197, 107, 101]) += "Åke" +>> Text.from_utf16([12371, 12435, 12395, 12385, 12399, 19990, 30028]) += "こんにちは世界".utf16() + +``` +## Text.from_utf32 ```tomo -Text.from_codepoints : func(codepoints: [Int32] -> [Text]) +Text.from_utf32 : func(codepoints: [Int32] -> [Text]) ``` Returns text that has been constructed from the given UTF32 codepoints. @@ -344,7 +325,30 @@ codepoints | `[Int32]` | The UTF32 codepoints in the desired text. | - **Example:** ```tomo ->> Text.from_codepoints([197, 107, 101]) +>> Text.from_utf32([197, 107, 101]) += "Åke" + +``` +## Text.from_utf8 + +```tomo +Text.from_utf8 : func(bytes: [Byte] -> [Text]) +``` + +Returns text that has been constructed from the given UTF8 bytes. + +The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input. + +Argument | Type | Description | Default +---------|------|-------------|--------- +bytes | `[Byte]` | The UTF-8 bytes of the desired text. | - + +**Return:** A new text based on the input UTF8 bytes after normalization has been applied. + + +**Example:** +```tomo +>> Text.from_utf8([195, 133, 107, 101]) = "Åke" ``` @@ -864,10 +868,33 @@ language | `Text` | The ISO 639 language code for which casing rules to use. | = "İ" ``` -## Text.utf32_codepoints +## Text.utf16 ```tomo -Text.utf32_codepoints : func(text: Text -> [Int32]) +Text.utf16 : func(text: Text -> [Int16]) +``` + +Returns a list of Unicode code points for UTF16 encoding of the text. + +Argument | Type | Description | Default +---------|------|-------------|--------- +text | `Text` | The text from which to extract Unicode code points. | - + +**Return:** A list of 16-bit integer Unicode code points (`[Int16]`). + + +**Example:** +```tomo +>> "Åke".utf16() += [197, 107, 101] +>> "こんにちは世界".utf16() += [12371, 12435, 12395, 12385, 12399, 19990, 30028] + +``` +## Text.utf32 + +```tomo +Text.utf32 : func(text: Text -> [Int32]) ``` Returns a list of Unicode code points for UTF32 encoding of the text. @@ -881,10 +908,31 @@ text | `Text` | The text from which to extract Unicode code points. | - **Example:** ```tomo ->> "Amélie".utf32_codepoints() +>> "Amélie".utf32() = [65, 109, 233, 108, 105, 101] ``` +## Text.utf8 + +```tomo +Text.utf8 : func(text: Text -> [Byte]) +``` + +Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text. + +Argument | Type | Description | Default +---------|------|-------------|--------- +text | `Text` | The text to be converted to UTF8 bytes. | - + +**Return:** A list of bytes (`[Byte]`) representing the text in UTF8 encoding. + + +**Example:** +```tomo +>> "Amélie".utf8() += [65, 109, 195, 169, 108, 105, 101] + +``` ## Text.width ```tomo diff --git a/api/text.yaml b/api/text.yaml index c8d70f0b..d209f4b3 100644 --- a/api/text.yaml +++ b/api/text.yaml @@ -129,7 +129,7 @@ Text.by_split_any: # Prints: "one" then "two" then "three": say(chunk) -Text.bytes: +Text.utf8: short: get UTF8 bytes description: > Converts a `Text` value to a list of bytes representing a UTF8 encoding of @@ -144,7 +144,7 @@ Text.bytes: description: > The text to be converted to UTF8 bytes. example: | - >> "Amélie".bytes() + >> "Amélie".utf8() = [65, 109, 195, 169, 108, 105, 101] Text.caseless_equals: @@ -255,7 +255,7 @@ Text.from: >> "hello".from(-2) = "lo" -Text.from_bytes: +Text.from_utf8: short: convert UTF8 byte list to text description: > Returns text that has been constructed from the given UTF8 bytes. @@ -272,9 +272,31 @@ Text.from_bytes: description: > The UTF-8 bytes of the desired text. example: | - >> Text.from_bytes([195, 133, 107, 101]) + >> Text.from_utf8([195, 133, 107, 101]) = "Åke" +Text.from_utf16: + short: convert UTF16 list to text + description: > + Returns text that has been constructed from the given UTF16 sequence. + note: > + The text will be normalized, so the resulting text's UTF16 sequence may not + exactly match the input. + return: + type: '[Text]' + description: > + A new text based on the input UTF16 sequence after normalization has been applied. + args: + bytes: + type: '[Int16]' + description: > + The UTF-16 integers of the desired text. + example: | + >> Text.from_utf16([197, 107, 101]) + = "Åke" + >> Text.from_utf16([12371, 12435, 12395, 12385, 12399, 19990, 30028]) + = "こんにちは世界".utf16() + Text.from_c_string: short: convert C-style string to text description: > @@ -318,7 +340,7 @@ Text.from_codepoint_names: ] = "Åke" -Text.from_codepoints: +Text.from_utf32: short: convert UTF32 codepoints to text description: > Returns text that has been constructed from the given UTF32 codepoints. @@ -335,7 +357,7 @@ Text.from_codepoints: description: > The UTF32 codepoints in the desired text. example: | - >> Text.from_codepoints([197, 107, 101]) + >> Text.from_utf32([197, 107, 101]) = "Åke" Text.has: @@ -906,7 +928,26 @@ Text.upper: >> "i".upper(language="tr_TR") = "İ" -Text.utf32_codepoints: +Text.utf16: + short: get UTF16 codepoints + description: > + Returns a list of Unicode code points for UTF16 encoding of the text. + return: + type: '[Int16]' + description: > + A list of 16-bit integer Unicode code points (`[Int16]`). + args: + text: + type: 'Text' + description: > + The text from which to extract Unicode code points. + example: | + >> "Åke".utf16() + = [197, 107, 101] + >> "こんにちは世界".utf16() + = [12371, 12435, 12395, 12385, 12399, 19990, 30028] + +Text.utf32: short: get UTF32 codepoints description: > Returns a list of Unicode code points for UTF32 encoding of the text. @@ -920,7 +961,7 @@ Text.utf32_codepoints: description: > The text from which to extract Unicode code points. example: | - >> "Amélie".utf32_codepoints() + >> "Amélie".utf32() = [65, 109, 233, 108, 105, 101] Text.width: |