diff --git a/icu4c/source/tools/genbrk/genbrk.1.in b/icu4c/source/tools/genbrk/genbrk.1.in new file mode 100644 index 0000000000..90f3f6b8ac --- /dev/null +++ b/icu4c/source/tools/genbrk/genbrk.1.in @@ -0,0 +1,119 @@ +.\" Hey, Emacs! This is -*-nroff-*- you know... +.\" +.\" genbrk.1: manual page for the genbrk utility +.\" +.\" Copyright (C) 2005-2005 IBM, Inc. and others. +.\" +.TH GENBRK 1 "2 December 2005" "ICU MANPAGE" "ICU @VERSION@ Manual" +.SH NAME +.B genbrk +\- Read in break iteration rules file and write out a binary data file +.SH SYNOPSIS +.B genbrk +[ +.BR "\-h\fP, \fB\-?\fP, \fB\-\-help" +] +[ +.BR "\-V\fP, \fB\-\-version" +] +[ +.BR "\-c\fP, \fB\-\-copyright" +] +[ +.BR "\-v\fP, \fB\-\-verbose" +] +[ +.BI "\-d\fP, \fB\-\-destdir" " destination" +] +[ +.BI "\-i\fP, \fB\-\-icudatadir" " directory" +] +.BI "\-r\fP, \fB\-\-rules" " rule\-file" +.BI "\-o\fP, \fB\-\-out" " output\-file" +.SH DESCRIPTION +.B genbrk +reads the text break rule text from +.I rule-file +and creates a break iteration data file. Normally this data file has the +.B .brk +extension. +.PP +The details of the rule syntax can be found in ICU's User Guide. +.SH OPTIONS +.TP +.BR "\-h\fP, \fB\-?\fP, \fB\-\-help" +Print help about usage and exit. +.TP +.BR "\-V\fP, \fB\-\-version" +Print the version of +.B genbrk +and exit. +.TP +.BR "\-c\fP, \fB\-\-copyright" +Embeds the standard ICU copyright into the +.IR output-file . +.TP +.BR "\-v\fP, \fB\-\-verbose" +Display extra informative messages during execution. +.TP +.BI "\-d\fP, \fB\-\-destdir" " destination" +Set the destination directory of the +.IR output-file +to +.IR destination . +.TP +.BI "\-i\fP, \fB\-\-icudatadir" " directory" +Look for any necessary ICU data files in +.IR directory . +For example, the file +.B pnames.icu +must be located when ICU's data is not built as a shared library. +The default ICU data directory is specified by the environment variable +.BR ICU_DATA . +Most configurations of ICU do not require this argument. +.TP +.BI "\-r\fP, \fB\-\-rules" " rule\-file" +The source file to read. +.TP +.BI "\-o\fP, \fB\-\-out" " output\-file" +The output data file to write. +.SH CAVEATS +When the +.IR rule-file +contains a byte order mark (BOM) at the beginning of the file, which is the Unicode character +.B U+FEFF, +then the +.IR rule-file +is interpreted as Unicode. Without the BOM, +the file is interpreted in the current operating system default codepage. +In order to eliminate any ambiguity of the encoding for how the +.IR rule-file +was written, it is recommended that you write this file in UTF-8 +with the BOM. +.SH INVARIANT CHARACTERS +The +.B invariant character set +consists of the following set of characters, expressed as a standard POSIX +regular expression: +.BR "[a-z]|[A-Z]|[0-9]|_| |+|-|*|/" . +This is the set which is guaranteed to be available regardless of code page. +.SH ENVIRONMENT +.TP 10 +.B ICU_DATA +Specifies the directory containing ICU data. Defaults to +.BR @thepkgicudatadir@/@PACKAGE@/@VERSION@/ . +Some tools in ICU depend on the presence of the trailing slash. It is thus +important to make sure that it is present if +.B ICU_DATA +is set. +.SH AUTHORS +George Rhoten +.br +Andy Heninger +.SH VERSION +1.0 +.SH COPYRIGHT +Copyright (C) 2005 IBM, Inc. and others. +.SH SEE ALSO +.BR http://icu.sourceforge.net/userguide/boundaryAnalysis.html +