From d64dcab138a34d5f5105e08f0a840f7cb5a1d159 Mon Sep 17 00:00:00 2001
From: Bruce Hill <bruce@bruce-hill.com>
Date: Tue, 9 Sep 2025 19:58:07 -0400
Subject: Overhaul to the unicode encoding/decoding methods for text

---
 man/man3/tomo-Text.bytes.3            | 34 ------------------------------
 man/man3/tomo-Text.from_bytes.3       | 37 ---------------------------------
 man/man3/tomo-Text.from_codepoints.3  | 37 ---------------------------------
 man/man3/tomo-Text.from_utf16.3       | 39 +++++++++++++++++++++++++++++++++++
 man/man3/tomo-Text.from_utf32.3       | 37 +++++++++++++++++++++++++++++++++
 man/man3/tomo-Text.from_utf8.3        | 37 +++++++++++++++++++++++++++++++++
 man/man3/tomo-Text.utf16.3            | 36 ++++++++++++++++++++++++++++++++
 man/man3/tomo-Text.utf32.3            | 34 ++++++++++++++++++++++++++++++
 man/man3/tomo-Text.utf32_codepoints.3 | 34 ------------------------------
 man/man3/tomo-Text.utf8.3             | 34 ++++++++++++++++++++++++++++++
 10 files changed, 217 insertions(+), 142 deletions(-)
 delete mode 100644 man/man3/tomo-Text.bytes.3
 delete mode 100644 man/man3/tomo-Text.from_bytes.3
 delete mode 100644 man/man3/tomo-Text.from_codepoints.3
 create mode 100644 man/man3/tomo-Text.from_utf16.3
 create mode 100644 man/man3/tomo-Text.from_utf32.3
 create mode 100644 man/man3/tomo-Text.from_utf8.3
 create mode 100644 man/man3/tomo-Text.utf16.3
 create mode 100644 man/man3/tomo-Text.utf32.3
 delete mode 100644 man/man3/tomo-Text.utf32_codepoints.3
 create mode 100644 man/man3/tomo-Text.utf8.3

(limited to 'man')

diff --git a/man/man3/tomo-Text.bytes.3 b/man/man3/tomo-Text.bytes.3
deleted file mode 100644
index f9203ef3..00000000
--- a/man/man3/tomo-Text.bytes.3
+++ /dev/null
@@ -1,34 +0,0 @@
-'\" t
-.\" Copyright (c) 2025 Bruce Hill
-.\" All rights reserved.
-.\"
-.TH Text.bytes 3 2025-04-30 "Tomo man-pages"
-.SH NAME
-Text.bytes \- get UTF8 bytes
-.SH LIBRARY
-Tomo Standard Library
-.SH SYNOPSIS
-.nf
-.BI Text.bytes\ :\ func(text:\ Text\ ->\ [Byte])
-.fi
-.SH DESCRIPTION
-Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text.
-
-
-.SH ARGUMENTS
-
-.TS
-allbox;
-lb lb lbx lb
-l l l l.
-Name	Type	Description	Default
-text	Text	The text to be converted to UTF8 bytes. 	-
-.TE
-.SH RETURN
-A list of bytes (`[Byte]`) representing the text in UTF8 encoding.
-
-.SH EXAMPLES
-.EX
->> "Amélie".bytes()
-= [65, 109, 195, 169, 108, 105, 101]
-.EE
diff --git a/man/man3/tomo-Text.from_bytes.3 b/man/man3/tomo-Text.from_bytes.3
deleted file mode 100644
index eec3843a..00000000
--- a/man/man3/tomo-Text.from_bytes.3
+++ /dev/null
@@ -1,37 +0,0 @@
-'\" t
-.\" Copyright (c) 2025 Bruce Hill
-.\" All rights reserved.
-.\"
-.TH Text.from_bytes 3 2025-04-30 "Tomo man-pages"
-.SH NAME
-Text.from_bytes \- convert UTF8 byte list to text
-.SH LIBRARY
-Tomo Standard Library
-.SH SYNOPSIS
-.nf
-.BI Text.from_bytes\ :\ func(bytes:\ [Byte]\ ->\ [Text])
-.fi
-.SH DESCRIPTION
-Returns text that has been constructed from the given UTF8 bytes.
-
-
-.SH ARGUMENTS
-
-.TS
-allbox;
-lb lb lbx lb
-l l l l.
-Name	Type	Description	Default
-bytes	[Byte]	The UTF-8 bytes of the desired text. 	-
-.TE
-.SH RETURN
-A new text based on the input UTF8 bytes after normalization has been applied.
-
-.SH NOTES
-The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input.
-
-.SH EXAMPLES
-.EX
->> Text.from_bytes([195, 133, 107, 101])
-= "Åke"
-.EE
diff --git a/man/man3/tomo-Text.from_codepoints.3 b/man/man3/tomo-Text.from_codepoints.3
deleted file mode 100644
index d64abd98..00000000
--- a/man/man3/tomo-Text.from_codepoints.3
+++ /dev/null
@@ -1,37 +0,0 @@
-'\" t
-.\" Copyright (c) 2025 Bruce Hill
-.\" All rights reserved.
-.\"
-.TH Text.from_codepoints 3 2025-04-30 "Tomo man-pages"
-.SH NAME
-Text.from_codepoints \- convert UTF32 codepoints to text
-.SH LIBRARY
-Tomo Standard Library
-.SH SYNOPSIS
-.nf
-.BI Text.from_codepoints\ :\ func(codepoints:\ [Int32]\ ->\ [Text])
-.fi
-.SH DESCRIPTION
-Returns text that has been constructed from the given UTF32 codepoints.
-
-
-.SH ARGUMENTS
-
-.TS
-allbox;
-lb lb lbx lb
-l l l l.
-Name	Type	Description	Default
-codepoints	[Int32]	The UTF32 codepoints in the desired text. 	-
-.TE
-.SH RETURN
-A new text with the specified codepoints after normalization has been applied.
-
-.SH NOTES
-The text will be normalized, so the resulting text's codepoints may not exactly match the input codepoints.
-
-.SH EXAMPLES
-.EX
->> Text.from_codepoints([197, 107, 101])
-= "Åke"
-.EE
diff --git a/man/man3/tomo-Text.from_utf16.3 b/man/man3/tomo-Text.from_utf16.3
new file mode 100644
index 00000000..d4eaea02
--- /dev/null
+++ b/man/man3/tomo-Text.from_utf16.3
@@ -0,0 +1,39 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.from_utf16 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.from_utf16 \- convert UTF16 list to text
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.from_utf16\ :\ func(bytes:\ [Int16]\ ->\ [Text])
+.fi
+.SH DESCRIPTION
+Returns text that has been constructed from the given UTF16 sequence.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+bytes	[Int16]	The UTF-16 integers of the desired text. 	-
+.TE
+.SH RETURN
+A new text based on the input UTF16 sequence after normalization has been applied.
+
+.SH NOTES
+The text will be normalized, so the resulting text's UTF16 sequence may not exactly match the input.
+
+.SH EXAMPLES
+.EX
+>> 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()
+.EE
diff --git a/man/man3/tomo-Text.from_utf32.3 b/man/man3/tomo-Text.from_utf32.3
new file mode 100644
index 00000000..31fc344f
--- /dev/null
+++ b/man/man3/tomo-Text.from_utf32.3
@@ -0,0 +1,37 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.from_utf32 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.from_utf32 \- convert UTF32 codepoints to text
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.from_utf32\ :\ func(codepoints:\ [Int32]\ ->\ [Text])
+.fi
+.SH DESCRIPTION
+Returns text that has been constructed from the given UTF32 codepoints.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+codepoints	[Int32]	The UTF32 codepoints in the desired text. 	-
+.TE
+.SH RETURN
+A new text with the specified codepoints after normalization has been applied.
+
+.SH NOTES
+The text will be normalized, so the resulting text's codepoints may not exactly match the input codepoints.
+
+.SH EXAMPLES
+.EX
+>> Text.from_utf32([197, 107, 101])
+= "Åke"
+.EE
diff --git a/man/man3/tomo-Text.from_utf8.3 b/man/man3/tomo-Text.from_utf8.3
new file mode 100644
index 00000000..ead65dc6
--- /dev/null
+++ b/man/man3/tomo-Text.from_utf8.3
@@ -0,0 +1,37 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.from_utf8 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.from_utf8 \- convert UTF8 byte list to text
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.from_utf8\ :\ func(bytes:\ [Byte]\ ->\ [Text])
+.fi
+.SH DESCRIPTION
+Returns text that has been constructed from the given UTF8 bytes.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+bytes	[Byte]	The UTF-8 bytes of the desired text. 	-
+.TE
+.SH RETURN
+A new text based on the input UTF8 bytes after normalization has been applied.
+
+.SH NOTES
+The text will be normalized, so the resulting text's UTF8 bytes may not exactly match the input.
+
+.SH EXAMPLES
+.EX
+>> Text.from_utf8([195, 133, 107, 101])
+= "Åke"
+.EE
diff --git a/man/man3/tomo-Text.utf16.3 b/man/man3/tomo-Text.utf16.3
new file mode 100644
index 00000000..2b3da2b1
--- /dev/null
+++ b/man/man3/tomo-Text.utf16.3
@@ -0,0 +1,36 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.utf16 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.utf16 \- get UTF16 codepoints
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.utf16\ :\ func(text:\ Text\ ->\ [Int16])
+.fi
+.SH DESCRIPTION
+Returns a list of Unicode code points for UTF16 encoding of the text.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+text	Text	The text from which to extract Unicode code points. 	-
+.TE
+.SH RETURN
+A list of 16-bit integer Unicode code points (`[Int16]`).
+
+.SH EXAMPLES
+.EX
+>> "Åke".utf16()
+= [197, 107, 101]
+>> "こんにちは世界".utf16()
+= [12371, 12435, 12395, 12385, 12399, 19990, 30028]
+.EE
diff --git a/man/man3/tomo-Text.utf32.3 b/man/man3/tomo-Text.utf32.3
new file mode 100644
index 00000000..ff37ba9c
--- /dev/null
+++ b/man/man3/tomo-Text.utf32.3
@@ -0,0 +1,34 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.utf32 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.utf32 \- get UTF32 codepoints
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.utf32\ :\ func(text:\ Text\ ->\ [Int32])
+.fi
+.SH DESCRIPTION
+Returns a list of Unicode code points for UTF32 encoding of the text.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+text	Text	The text from which to extract Unicode code points. 	-
+.TE
+.SH RETURN
+A list of 32-bit integer Unicode code points (`[Int32]`).
+
+.SH EXAMPLES
+.EX
+>> "Amélie".utf32()
+= [65, 109, 233, 108, 105, 101]
+.EE
diff --git a/man/man3/tomo-Text.utf32_codepoints.3 b/man/man3/tomo-Text.utf32_codepoints.3
deleted file mode 100644
index 0ada8954..00000000
--- a/man/man3/tomo-Text.utf32_codepoints.3
+++ /dev/null
@@ -1,34 +0,0 @@
-'\" t
-.\" Copyright (c) 2025 Bruce Hill
-.\" All rights reserved.
-.\"
-.TH Text.utf32_codepoints 3 2025-04-30 "Tomo man-pages"
-.SH NAME
-Text.utf32_codepoints \- get UTF32 codepoints
-.SH LIBRARY
-Tomo Standard Library
-.SH SYNOPSIS
-.nf
-.BI Text.utf32_codepoints\ :\ func(text:\ Text\ ->\ [Int32])
-.fi
-.SH DESCRIPTION
-Returns a list of Unicode code points for UTF32 encoding of the text.
-
-
-.SH ARGUMENTS
-
-.TS
-allbox;
-lb lb lbx lb
-l l l l.
-Name	Type	Description	Default
-text	Text	The text from which to extract Unicode code points. 	-
-.TE
-.SH RETURN
-A list of 32-bit integer Unicode code points (`[Int32]`).
-
-.SH EXAMPLES
-.EX
->> "Amélie".utf32_codepoints()
-= [65, 109, 233, 108, 105, 101]
-.EE
diff --git a/man/man3/tomo-Text.utf8.3 b/man/man3/tomo-Text.utf8.3
new file mode 100644
index 00000000..80a91fb9
--- /dev/null
+++ b/man/man3/tomo-Text.utf8.3
@@ -0,0 +1,34 @@
+'\" t
+.\" Copyright (c) 2025 Bruce Hill
+.\" All rights reserved.
+.\"
+.TH Text.utf8 3 2025-09-09 "Tomo man-pages"
+.SH NAME
+Text.utf8 \- get UTF8 bytes
+.SH LIBRARY
+Tomo Standard Library
+.SH SYNOPSIS
+.nf
+.BI Text.utf8\ :\ func(text:\ Text\ ->\ [Byte])
+.fi
+.SH DESCRIPTION
+Converts a `Text` value to a list of bytes representing a UTF8 encoding of the text.
+
+
+.SH ARGUMENTS
+
+.TS
+allbox;
+lb lb lbx lb
+l l l l.
+Name	Type	Description	Default
+text	Text	The text to be converted to UTF8 bytes. 	-
+.TE
+.SH RETURN
+A list of bytes (`[Byte]`) representing the text in UTF8 encoding.
+
+.SH EXAMPLES
+.EX
+>> "Amélie".utf8()
+= [65, 109, 195, 169, 108, 105, 101]
+.EE
-- 
cgit v1.2.3