mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-19 03:34:38 +00:00
ICU-3650 Update gencnval and alias table documentation
X-SVN-Rev: 14691
This commit is contained in:
parent
2546c71963
commit
123c565384
3 changed files with 20 additions and 152 deletions
|
@ -19,14 +19,12 @@ subdir = tools/gencnval
|
|||
SECTION = 1
|
||||
|
||||
MANX_FILES = $(TARGET:$(EXEEXT)=).$(SECTION)
|
||||
MAN5_FILES = convrtrs.txt.5
|
||||
|
||||
GENERATED_MAN_FILES = $(TARGET).$(SECTION) convrtrs.txt.5
|
||||
GENERATED_MAN_FILES = $(TARGET).$(SECTION)
|
||||
|
||||
ALL_MAN_FILES = $(MANX_FILES) $(MAN5_FILES)
|
||||
ALL_MAN_FILES = $(MANX_FILES)
|
||||
|
||||
ICUDATADIR=$(top_builddir)/data/
|
||||
CONVRTRSFILE=$(top_srcdir)/../data/convrtrs.txt
|
||||
|
||||
## Extra files to remove for 'make clean'
|
||||
CLEANFILES = *~ $(GENERATED_MAN_FILES) $(DEPS) $(RES_FILES) $(TEST_FILES)
|
||||
|
@ -45,7 +43,7 @@ DEPS = $(OBJECTS:.o=.d)
|
|||
## List of phony targets
|
||||
.PHONY : all all-local install install-local clean clean-local \
|
||||
distclean distclean-local dist dist-local check \
|
||||
check-local build-data install-man install-man5 install-manx
|
||||
check-local build-data install-man install-manx
|
||||
|
||||
## Clear suffix list
|
||||
.SUFFIXES :
|
||||
|
@ -84,10 +82,7 @@ $(TARGET) : $(OBJECTS)
|
|||
$(LINK.cc) $(OUTOPT)$@ $^ $(LIBS)
|
||||
|
||||
# man page
|
||||
install-man: install-man5 install-manx
|
||||
install-man5: $(MAN5_FILES)
|
||||
$(MKINSTALLDIRS) $(DESTDIR)$(mandir)/man5
|
||||
$(INSTALL_DATA) $? $(DESTDIR)$(mandir)/man5
|
||||
install-man: install-manx
|
||||
install-manx: $(MANX_FILES)
|
||||
$(MKINSTALLDIRS) $(DESTDIR)$(mandir)/man$(SECTION)
|
||||
$(INSTALL_DATA) $? $(DESTDIR)$(mandir)/man$(SECTION)
|
||||
|
@ -95,9 +90,6 @@ install-manx: $(MANX_FILES)
|
|||
%.$(SECTION): $(srcdir)/%.$(SECTION).in
|
||||
cd $(top_builddir) \
|
||||
&& CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status
|
||||
%.5: $(srcdir)/%.5.in
|
||||
cd $(top_builddir) \
|
||||
&& CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status
|
||||
|
||||
# only on linux probably ?
|
||||
#$(TARGET).ps: $(TARGET).$(SECTION)
|
||||
|
|
|
@ -1,131 +0,0 @@
|
|||
.\" Hey, Emacs! This is -*-nroff-*- you know...
|
||||
.\"
|
||||
.\" convrtrs.txt.5: manual page for the convrtrs.txt file
|
||||
.\"
|
||||
.\" Copyright (C) 2000-2002 IBM, Inc. and others.
|
||||
.\"
|
||||
.\" Manual page by Yves Arrouye <yves@realnames.com>.
|
||||
.\"
|
||||
.TH CONVRTRS.TXT 5 "22 July 2002" "ICU MANPAGE" "ICU @VERSION@ Manual"
|
||||
.SH NAME
|
||||
.B convrtrs.txt
|
||||
\- ICU converters aliases file
|
||||
.br
|
||||
.B cnvalias.icu
|
||||
\- binary ICU converters aliases file
|
||||
.SH DESCRIPTION
|
||||
The file
|
||||
.B convrtrs.txt
|
||||
lists the names of the converters that ICU can handle, along with
|
||||
their known aliases. ICU can open a converter given either its real name or
|
||||
any of its aliases.
|
||||
.B convrtrs.txt
|
||||
is read by
|
||||
.BR gencnval (1)
|
||||
in order to generate the binary data that ICU uses to represent the converters
|
||||
aliases information.
|
||||
.PP
|
||||
Each converter and its aliases are described on a separate lines; fields
|
||||
on each line are separated by white space. The order of records in
|
||||
.B convrtrs.txt
|
||||
is significant: if a given name appears multiple times, the last one prevails.
|
||||
Names of converters and aliases are compared without considering case; the
|
||||
characters dash (U+002D HYPHEN-MINUS), underscore (U+005F LOW LINE), and
|
||||
space (U+0020 SPACE) are also ignored during comparison
|
||||
(even though spaces cannot be used in
|
||||
.B convrtrs.txt
|
||||
since white space is significant as a field delimiter).
|
||||
Thus the names
|
||||
.BR UTF-8 ,
|
||||
.BR utf_8 ,
|
||||
and
|
||||
.BR "Utf 8"
|
||||
are equivalent converters names.
|
||||
.PP
|
||||
The format of
|
||||
.B convrtrs.txt
|
||||
can be described by the following BNF grammar:
|
||||
.PP
|
||||
.RS
|
||||
.nf
|
||||
converters ::= tags { converter }
|
||||
converter ::= name [ tags ] { alias }
|
||||
alias ::= name [ tags ]
|
||||
tags ::= '{' { tag } '}'
|
||||
tag ::= standard{*}
|
||||
comment ::= '#' \fIanything\fP
|
||||
.fi
|
||||
.RE
|
||||
.PP
|
||||
Line continuation and comment sytax are similar to the GNU make syntax.
|
||||
Any lines beginning with whitespace (e.g. U+0020 SPACE or U+0009 HORIZONTAL
|
||||
TABULATION) are presumed to be a continuation of the previous line.
|
||||
.PP
|
||||
The file must start with a list of recognized tags. These tags are used to
|
||||
get the correct converter implementation based on the defined standard tag.
|
||||
For instance, Shift-JIS on an IBM platform may be different from Shift-JIS
|
||||
on a Windows platform.
|
||||
.PP
|
||||
A
|
||||
.I name
|
||||
can use any character other than white space and the '{' and '#' delimiters.
|
||||
In practice, names are usually restricted to the set of uppercase and
|
||||
lowercase latin letters plus arabic digits, the dash, the underscore,
|
||||
and the colon characters. It is recommended to follow this convention
|
||||
when naming new converters or their aliases.
|
||||
.PP
|
||||
A
|
||||
.I comment
|
||||
starts with the pound character '#' and ends with the current
|
||||
line. Comments are ignored.
|
||||
.PP
|
||||
The
|
||||
.I name
|
||||
of a given
|
||||
.I converter
|
||||
must match its algorithmic name if the converter is algorithmic, or
|
||||
its file name if the converter is table-driven. The table for the
|
||||
converter
|
||||
.B ibm-912
|
||||
for example, is expected to be in the
|
||||
.B ibm-912.cnv
|
||||
file.
|
||||
An
|
||||
.I alias
|
||||
has no such restriction, as aliases are just arbitrary names
|
||||
associated to a given converter.
|
||||
.PP
|
||||
The presence of a
|
||||
.I tag
|
||||
after a converter or alias name means that this name is associated to
|
||||
a given standard set of names. Two well-known such standards are the
|
||||
.B MIME
|
||||
and
|
||||
.B IANA
|
||||
registries of names. The default ICU
|
||||
.B convrtrs.txt
|
||||
file already uses these tags.
|
||||
These tags must be declared at the beginning of the file.
|
||||
Names appropriate for a given standard can be retrieved
|
||||
programmatically by using the ucnv_getStandardName() or the
|
||||
ucnv_openStandardNames() function. The asterisk (U+002A) is
|
||||
used to note which standard name is the default, and the
|
||||
preceding alias is returned by ucnv_getStandardName(). A standard
|
||||
tag may have multiple aliases recognized by the same standard for
|
||||
the same converter name.
|
||||
.SH CAVEATS
|
||||
The
|
||||
.B convrtrs.txt
|
||||
file is not directly read by ICU. It must be transformed into a binary
|
||||
file by
|
||||
.BR gencnval (1)
|
||||
first. Also, depending on the way ICU was packaged, even the resulting
|
||||
.B cnvalias.icu
|
||||
file may not be read by ICU. Please refer to the ICU manual for more
|
||||
information on which files are effectively read by ICU at runtime, and
|
||||
how to produce them.
|
||||
.SH COPYRIGHT
|
||||
Copyright (C) 2000-2002 IBM, Inc. and others.
|
||||
.SH SEE ALSO
|
||||
.BR gencnval (1),
|
||||
.BR pkgdata (1)
|
|
@ -2,11 +2,12 @@
|
|||
.\"
|
||||
.\" gencnval.1: manual page for the gencnval utility
|
||||
.\"
|
||||
.\" Copyright (C) 2000 IBM, Inc. and others.
|
||||
.\" Copyright (C) 2000-2004 IBM, Inc. and others.
|
||||
.\"
|
||||
.\" Manual page by Yves Arrouye <yves@realnames.com>.
|
||||
.\" Manual page by George Rhoten
|
||||
.\"
|
||||
.TH GENCNVAL 1 "16 April 2002" "ICU MANPAGE" "ICU @VERSION@ Manual"
|
||||
.TH GENCNVAL 1 "11 March 2004" "ICU MANPAGE" "ICU @VERSION@ Manual"
|
||||
.SH NAME
|
||||
.B gencnval
|
||||
\- compile the converters aliases file
|
||||
|
@ -16,6 +17,9 @@
|
|||
.BR "\-h\fP, \fB\-?\fP, \fB\-\-help"
|
||||
]
|
||||
[
|
||||
.BR "\-v\fP, \fB\-\-verbose"
|
||||
]
|
||||
[
|
||||
.BR "\-c\fP, \fB\-\-copyright"
|
||||
]
|
||||
[
|
||||
|
@ -32,7 +36,7 @@
|
|||
converts the ICU aliases file
|
||||
.I converterfile
|
||||
into the binary file
|
||||
.BR cnvalias.dat .
|
||||
.BR cnvalias.icu .
|
||||
This binary file can then be read directly by ICU, or used by
|
||||
.BR pkgdata (1)
|
||||
for incorporation into a larger archive or library.
|
||||
|
@ -47,6 +51,10 @@ file is used.
|
|||
.BR "\-h\fP, \fB\-?\fP, \fB\-\-help"
|
||||
Print help about usage and exit.
|
||||
.TP
|
||||
.BR "\-v\fP, \fB\-\-verbose"
|
||||
Display verbose output. This information can include information about
|
||||
conflicting aliases and the converters the aliases resolve to.
|
||||
.TP
|
||||
.BR "\-c\fP, \fB\-\-copyright"
|
||||
Include a copyright notice in the binary data.
|
||||
.TP
|
||||
|
@ -71,14 +79,13 @@ important to make sure that it is present if
|
|||
.B ICU_DATA
|
||||
is set.
|
||||
.SH FILES
|
||||
.TP \w'\fB@thesysconfdir@/@PACKAGE@/convrtrs.txt'u+3n
|
||||
.B @thesysconfdir@/@PACKAGE@/convrtrs.txt
|
||||
Description of ICU's converters and their aliases.
|
||||
.TP \w'\fB@PACKAGE@/source/data/mappings/convrtrs.txt'u+3n
|
||||
.B @PACKAGE@/source/data/mappings/convrtrs.txt
|
||||
Description of ICU's converters and their aliases. This data file is not
|
||||
normally installed, and it is available as a part of ICU source code.
|
||||
.SH VERSION
|
||||
@VERSION@
|
||||
.SH COPYRIGHT
|
||||
Copyright (C) 2000-2002 IBM, Inc. and others.
|
||||
Copyright (C) 2000-2004 IBM, Inc. and others.
|
||||
.SH SEE ALSO
|
||||
.BR convrtrs.txt (5)
|
||||
.br
|
||||
.BR pkgdata (1)
|
||||
|
|
Loading…
Add table
Reference in a new issue