gbranden pushed a commit to branch master
in repository groff.
commit 0629380a9d464c74d6dd205384bc255e1015c2f4
Author: G. Branden Robinson <[email protected]>
AuthorDate: Sat Aug 3 18:36:42 2024 -0500
tmac/*: Refactor hyphenation code declarations.
Move `hcode` invocations from language-specific macro files (those that
define a "groff locale", such as "english" or "german") to the macro
files that support 8-bit character encodings, because in the formatter,
hyphenation codes are global, not environment-specific like other
hyphenation data. (That design decision is worth reconsidering in the
future, but feels less urgent than adding UTF-8 input support to the
formatter, which may obviate some encoding-related issues.)
* tmac/LOCALIZATION: Relieve groff locale contributor of hyphenation
code definition duty.
* tmac/de.tmac: Move Latin-1 hyphenation code definitions from here...
* tmac/latin1.tmac: ...to here. Reorganize and cover _every_ letter
glyph in ISO 8859-1, including Icelandic letters that German
hyphenation patterns don't require.
* tmac/ru.tmac: Move KOI8-R hyphenation code definitions from here...
* tmac/koi8-r.tmac: ...to here.
* tmac/latin2.tmac: Define Latin-2 hyphenation codes.
* tmac/latin5.tmac: Define Latin-5 hyphenation codes. Include the
notorious special case for the Turkish capital dotted I, and annotate
it for migration in the event we ever get a "tr.tmac" file, because
this is a language-specific case mapping, not one strictly implied by
the character encoding.
* tmac/latin9.tmac: Define Latin-9 (ISO 8859-15) hyphenation codes.
Thanks to Werner Lemberg for the discussion in <https://lists.gnu.org/
archive/html/groff/2024-08/msg00001.html>.
---
ChangeLog | 35 ++++++++++++++++++++
tmac/LOCALIZATION | 8 ++---
tmac/de.tmac | 18 -----------
tmac/koi8-r.tmac | 42 +++++++++++++++++++++++-
tmac/latin1.tmac | 67 +++++++++++++++++++++++++++++++++++++++
tmac/latin2.tmac | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
tmac/latin5.tmac | 75 ++++++++++++++++++++++++++++++++++++++++++-
tmac/latin9.tmac | 77 +++++++++++++++++++++++++++++++++++++++++++-
tmac/ru.tmac | 36 +--------------------
9 files changed, 391 insertions(+), 62 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 496be617a..b3c23e58a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,38 @@
+2024-08-03 G. Branden Robinson <[email protected]>
+
+ tmac/*: Refactor hyphenation code declarations.
+
+ Move `hcode` invocations from language-specific macro files
+ {those that define a "groff locale", such as "english" or
+ "german"} to the macro files that support 8-bit character
+ encodings, because in the formatter, hyphenation codes are
+ global, not environment-specific like other hyphenation data.
+ {That design decision is worth reconsidering in the future,
+ but feels less urgent than adding UTF-8 input support to the
+ formatter, which may obviate some encoding-related issues.}
+
+ * tmac/LOCALIZATION: Relieve groff locale contributor of
+ hyphenation code definition duty.
+ * tmac/de.tmac: Move Latin-1 hyphenation code definitions from
+ here...
+ * tmac/latin1.tmac: ...to here. Reorganize and cover _every_
+ letter glyph in ISO 8859-1, including Icelandic letters that
+ German hyphenation patterns don't require.
+ * tmac/ru.tmac: Move KOI8-R hyphenation code definitions from
+ here...
+ * tmac/koi8-r.tmac: ...to here.
+ * tmac/latin2.tmac: Define Latin-2 hyphenation codes.
+ * tmac/latin5.tmac: Define Latin-5 hyphenation codes. Include
+ the notorious special case for the Turkish capital dotted I, and
+ annotate it for migration in the event we ever get a "tr.tmac"
+ file, because this is a language-specific case mapping, not one
+ strictly implied by the character encoding.
+ * tmac/latin9.tmac: Define Latin-9 (ISO 8859-15) hyphenation
+ codes.
+
+ Thanks to Werner Lemberg for the discussion in <https://
+ lists.gnu.org/archive/html/groff/2024-08/msg00001.html>.
+
2024-07-31 G. Branden Robinson <[email protected]>
* src/roff/troff/input.cpp (set_hyphenation_codes): Accept a
diff --git a/tmac/LOCALIZATION b/tmac/LOCALIZATION
index f123fe716..ed9b6c5ca 100644
--- a/tmac/LOCALIZATION
+++ b/tmac/LOCALIZATION
@@ -20,12 +20,10 @@ hyphenation pattern files.
\lefthyphenmin=2, \righthyphenmin=2 => 1
\lefthyphenmin=2, \righthyphenmin=3 => 4
\lefthyphenmin=1, \righthyphenmin=2 => 32
- F. Hyphenation codes appropriate to the hyphenation pattern files
- for the locale are set with the .hcode request.
- G. The hyphenation language is set with the .hla request.
- H. Support for the character encoding used by the hyphenation
+ F. The hyphenation language is set with the .hla request.
+ G. Support for the character encoding used by the hyphenation
pattern files is loaded with the .mso request.
- I. Hyphenation pattern and exception files are loaded with the .hpf
+ H. Hyphenation pattern and exception files are loaded with the .hpf
and .hpfa requests.
2. A locale-independent file (trans.tmac) activates the localized
diff --git a/tmac/de.tmac b/tmac/de.tmac
index 64d6a2339..8a1169626 100644
--- a/tmac/de.tmac
+++ b/tmac/de.tmac
@@ -172,24 +172,6 @@
.
.rr locale*use-trap-hyphenation-mode
.
-.hcode � � � � � � � � � � � � � �
-.hcode � �
-.hcode � � � � � � � �
-.hcode � � � � � � � �
-.hcode � �
-.hcode � � � � � � � � � �
-.hcode � � � � � �
-.
-.hcode � � � � � � � � � � � � � �
-.hcode � �
-.hcode � � � � � � � �
-.hcode � � � � � � � �
-.hcode � �
-.hcode � � � � � � � � � �
-.hcode � � � � � �
-.
-.hcode � �
-.
.hla de
.ie r \*[locale]-new-hyphenation-patterns \
. hpf hyphen.den
diff --git a/tmac/koi8-r.tmac b/tmac/koi8-r.tmac
index dd1402908..ea9447858 100644
--- a/tmac/koi8-r.tmac
+++ b/tmac/koi8-r.tmac
@@ -71,11 +71,51 @@
.trin \[char253]\[u0429]
.trin \[char254]\[u0427]
.trin \[char255]\[u042A]
+.
+.\" Set up hyphenation codes for letter-like characters above.
+.\" Each small letter from KOI8-R gets its own hyphenation code; each
+.\" capital letter is assigned the code of its small counterpart.
+.
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.hcode � � � �
+.
.cp \n[*groff_koi8-r_tmac_C]
.do rr *groff_koi8-r_tmac_C
.
.\" Local Variables:
.\" mode: nroff
+.\" coding: cyrillic-koi8
.\" fill-column: 72
.\" End:
-.\" vim: set filetype=groff textwidth=72:
+.\" vim: set fileencoding=koi8-r filetype=groff textwidth=72:
diff --git a/tmac/latin1.tmac b/tmac/latin1.tmac
index 19e6e5e9d..6ade0582d 100644
--- a/tmac/latin1.tmac
+++ b/tmac/latin1.tmac
@@ -107,11 +107,78 @@
.trin \[char253]\['y]
.trin \[char254]\[Tp]
.trin \[char255]\[:y]
+.
+.\" Set up hyphenation codes for letter-like characters above.
+.\" Each small letter from ISO 8859-1 gets its own hyphenation code;
+.\" each capital letter is assigned the code of its small counterpart.
+.\" Some small letters have no capital form in the encoding.
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
.cp \n[*groff_latin1_tmac_C]
.do rr *groff_latin1_tmac_C
.
.\" Local Variables:
.\" mode: nroff
+.\" coding: latin-1
.\" fill-column: 72
.\" End:
.\" vim: set filetype=groff textwidth=72:
diff --git a/tmac/latin2.tmac b/tmac/latin2.tmac
index b45c7a962..ee81be0b0 100644
--- a/tmac/latin2.tmac
+++ b/tmac/latin2.tmac
@@ -233,11 +233,104 @@
.trin \[char253]\['y]
.trin \[char254]\[t ac]
.trin \[char255]\[a.]
+.
+.\" Set up hyphenation codes for letter-like characters above.
+.\" Each small letter from ISO 8859-2 gets its own hyphenation code;
+.\" each capital letter is assigned the code of its small counterpart.
+.\" Some small letters have no capital form in the encoding.
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
.cp \n[*groff_latin2_tmac_C]
.do rr *groff_latin2_tmac_C
.
.\" Local Variables:
.\" mode: nroff
+.\" coding: latin-2
.\" fill-column: 72
.\" End:
-.\" vim: set filetype=groff textwidth=72:
+.\" vim: set fileencoding=iso-8859-2 filetype=groff textwidth=72:
diff --git a/tmac/latin5.tmac b/tmac/latin5.tmac
index 0cdc63c5e..75ebb33c5 100644
--- a/tmac/latin5.tmac
+++ b/tmac/latin5.tmac
@@ -125,11 +125,84 @@
.trin \[char253]\[.i]
.trin \[char254]\[s ,]
.trin \[char255]\[:y]
+.
+.\" Set up hyphenation codes for letter-like characters above.
+.\" Each small letter from ISO 8859-9 gets its own hyphenation code;
+.\" each capital letter is assigned the code of its small counterpart.
+.\" Some small letters have no capital form in the encoding.
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � i \" exceptional case; move to tr.tmac if we ever get one
+.hcode � �
+.
.cp \n[*groff_latin5_tmac_C]
.do rr *groff_latin5_tmac_C
.
.\" Local Variables:
.\" mode: nroff
+.\" coding: latin-5
.\" fill-column: 72
.\" End:
-.\" vim: set filetype=groff textwidth=72:
+.\" vim: set fileencoding=iso-8859-9 filetype=groff textwidth=72:
diff --git a/tmac/latin9.tmac b/tmac/latin9.tmac
index 4b80075c5..be23f0d60 100644
--- a/tmac/latin9.tmac
+++ b/tmac/latin9.tmac
@@ -129,11 +129,86 @@
.trin \[char253]\['y]
.trin \[char254]\[Tp]
.trin \[char255]\[:y]
+.
+.\" Set up hyphenation codes for letter-like characters above.
+.\" Each small letter from ISO 8859-1 gets its own hyphenation code;
+.\" each capital letter is assigned the code of its small counterpart.
+.\" Some small letters have no capital form in the encoding.
+.
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.hcode � �
+.
.cp \n[*groff_latin9_tmac_C]
.do rr *groff_latin9_tmac_C
.
.\" Local Variables:
.\" mode: nroff
+.\" coding: latin-9
.\" fill-column: 72
.\" End:
-.\" vim: set filetype=groff textwidth=72:
+.\" vim: set fileencoding=iso-8859-15 filetype=groff textwidth=72:
diff --git a/tmac/ru.tmac b/tmac/ru.tmac
index 2914072ed..b55c1eec6 100644
--- a/tmac/ru.tmac
+++ b/tmac/ru.tmac
@@ -182,39 +182,6 @@ Cyrillic script
. \}
.\}
.
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
-.hcode � � � �
.
.hla ru
.hpf hyphen.ru
@@ -240,5 +207,4 @@ Cyrillic script
.\" coding: cyrillic-koi8
.\" fill-column: 72
.\" End:
-.\" XXX: Vim 8.2 does not handle koi8-r correctly.
-.\" vim: set filetype=groff textwidth=72:
+.\" vim: set fileencoding=koi8-r filetype=groff textwidth=72:
_______________________________________________
Groff-commit mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/groff-commit
