icuSources/tools/gendict/gendict.1.in

   1 .\" Hey, Emacs! This is -*-nroff-*- you know...
   2 .\"
   3 .\" gendict.1: manual page for the gendict utility
   4 .\"
   5 .\" Copyright (C) 2016 and later: Unicode, Inc. and others.
   6 .\" License & terms of use: http://www.unicode.org/copyright.html
   7 .\" Copyright (C) 2012 International Business Machines Corporation and others
   8 .\"
   9 .TH GENDICT 1 "1 June 2012" "ICU MANPAGE" "ICU @VERSION@ Manual"
  10 .SH NAME
  11 .B gendict
  12 \- Compiles word list into ICU string trie dictionary
  13 .SH SYNOPSIS
  14 .B gendict
  15 [
  16 .BR "\fB\-\-uchars"
  17 |
  18 .BR "\fB\-\-bytes"
  19 .BI "\fB\-\-transform" " transform"
  20 ]
  21 [
  22 .BR "\-h\fP, \fB\-?\fP, \fB\-\-help"
  23 ]
  24 [
  25 .BR "\-V\fP, \fB\-\-version"
  26 ]
  27 [
  28 .BR "\-c\fP, \fB\-\-copyright"
  29 ]
  30 [
  31 .BR "\-v\fP, \fB\-\-verbose"
  32 ]
  33 [
  34 .BI "\-i\fP, \fB\-\-icudatadir" " directory"
  35 ]
  36 .IR " input-file"
  37 .IR " output\-file"
  38 .SH DESCRIPTION
  39 .B gendict
  40 reads the word list from
  41 .I dictionary-file
  42 and creates a string trie dictionary file. Normally this data file has the
  43 .B .dict
  44 extension.
  45 .PP
  46 Words begin at the beginning of a line and are terminated by the first whitespace.
  47 Lines that begin with whitespace are ignored.
  48 .SH OPTIONS
  49 .TP
  50 .BR "\-h\fP, \fB\-?\fP, \fB\-\-help"
  51 Print help about usage and exit.
  52 .TP
  53 .BR "\-V\fP, \fB\-\-version"
  54 Print the version of
  55 .B gendict
  56 and exit.
  57 .TP
  58 .BR "\-c\fP, \fB\-\-copyright"
  59 Embeds the standard ICU copyright into the
  60 .IR output-file .
  61 .TP
  62 .BR "\-v\fP, \fB\-\-verbose"
  63 Display extra informative messages during execution.
  64 .TP
  65 .BI "\-i\fP, \fB\-\-icudatadir" " directory"
  66 Look for any necessary ICU data files in
  67 .IR directory .
  68 For example, the file
  69 .B pnames.icu
  70 must be located when ICU's data is not built as a shared library.
  71 The default ICU data directory is specified by the environment variable
  72 .BR ICU_DATA .
  73 Most configurations of ICU do not require this argument.
  74 .TP
  75 .BR "\fB\-\-uchars"
  76 Set the output trie type to UChar. Mutually exclusive with
  77 .BR --bytes.
  78 .TP
  79 .BR "\fB\-\-bytes"
  80 Set the output trie type to Bytes. Mutually exclusive with
  81 .BR --uchars.
  82 .TP
  83 .BR "\fB\-\-transform"
  84 Set the transform type. Should only be specified with
  85 .BR --bytes.
  86 Currently supported transforms are:
  87 .BR offset-<hex-number>,
  88 which specifies an offset to subtract from all input characters.
  89 It should be noted that the offset transform also maps U+200D
  90 to 0xFF and U+200C to 0xFE, in order to offer compatibility to
  91 languages that require these characters.
  92 A transform must be specified for a bytes trie, and when applied
  93 to the non-value characters in the
  94 .IR input-file
  95 must produce output between 0x00 and 0xFF.
  96 .TP
  97 .BI " input\-file"
  98 The source file to read.
  99 .TP
 100 .BI " output\-file"
 101 The file to write the output dictionary to.
 102 .SH CAVEATS
 103 The
 104 .IR input-file
 105 is assumed to be encoded in UTF-8.
 106 The integers in the
 107 .IR input-file
 108 that are used as values must be made up of ASCII digits. They
 109 may be specified either in hex, by using a 0x prefix, or in
 110 decimal.
 111 Either
 112 .BI --bytes
 113 or
 114 .BI --uchars
 115 must be specified.
 116 .SH ENVIRONMENT
 117 .TP 10
 118 .B ICU_DATA
 119 Specifies the directory containing ICU data. Defaults to
 120 .BR @thepkgicudatadir@/@PACKAGE@/@VERSION@/ .
 121 Some tools in ICU depend on the presence of the trailing slash. It is thus
 122 important to make sure that it is present if
 123 .B ICU_DATA
 124 is set.
 125 .SH AUTHORS
 126 Maxime Serrano
 127 .SH VERSION
 128 1.0
 129 .SH COPYRIGHT
 130 Copyright (C) 2012 International Business Machines Corporation and others
 131 .SH SEE ALSO
 132 .BR http://www.icu-project.org/userguide/boundaryAnalysis.html
 133