{ "content": [ { "type": "text", "text": "# gendict (man)\n\n## NAME\n\ngendict - Compiles word list into ICU string trie dictionary\n\n## SYNOPSIS\n\ngendict [ --uchars | --bytes --transform transform ] [ -h, -?, --help ] [ -V, --version ] [\n\n## DESCRIPTION\n\ngendict reads the word list from dictionary-file and creates a string trie dictionary file.\nNormally this data file has the .dict extension.\n\n## Sections\n\n- **NAME**\n- **SYNOPSIS** (1 subsections)\n- **DESCRIPTION**\n- **OPTIONS** (10 subsections)\n- **CAVEATS**\n- **ENVIRONMENT**\n- **AUTHORS**\n- **VERSION**\n- **COPYRIGHT**\n- **SEE ALSO** (1 subsections)\n\nUse structuredContent.sections for detailed options, examples, and full documentation.\n" } ], "structuredContent": { "command": "gendict", "section": "", "mode": "man", "summary": "gendict - Compiles word list into ICU string trie dictionary", "synopsis": "gendict [ --uchars | --bytes --transform transform ] [ -h, -?, --help ] [ -V, --version ] [", "tldr_summary": null, "tldr_examples": [], "tldr_source": null, "flags": [ { "flag": "-?", "long": "--help", "arg": null, "description": "Print help about usage and exit." }, { "flag": "-V", "long": "--version", "arg": null, "description": "Print the version of gendict and exit." }, { "flag": "-c", "long": "--copyright", "arg": null, "description": "Embeds the standard ICU copyright into the output-file." }, { "flag": "-v", "long": "--verbose", "arg": null, "description": "Display extra informative messages during execution." }, { "flag": "-i", "long": "--icudatadir", "arg": null, "description": "Look for any necessary ICU data files in directory. For example, the file 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 ICUDATA. Most configurations of ICU do not require this argument." }, { "flag": "", "long": "--uchars", "arg": null, "description": "Set the output trie type to UChar. Mutually exclusive with --bytes." }, { "flag": "", "long": "--bytes", "arg": null, "description": "Set the output trie type to Bytes. Mutually exclusive with --uchars." }, { "flag": "", "long": "--transform", "arg": null, "description": "Set the transform type. Should only be specified with --bytes. Currently supported transforms are: offset-, which specifies an offset to subtract from all input characters. It should be noted that the offset transform also maps U+200D to 0xFF and U+200C to 0xFE, in order to offer compatibility to languages that require these characters. A transform must be specified for a bytes trie, and when applied to the non-value characters in the input-file must produce output between 0x00 and 0xFF." } ], "examples": [], "see_also": [], "section_outline": [ { "name": "NAME", "lines": 2, "subsections": [] }, { "name": "SYNOPSIS", "lines": 1, "subsections": [ { "name": "-c --copyright -v --verbose -i --icudatadir", "lines": 1, "flag": "-i", "long": "--icudatadir" } ] }, { "name": "DESCRIPTION", "lines": 6, "subsections": [] }, { "name": "OPTIONS", "lines": 1, "subsections": [ { "name": "-h -? --help", "lines": 2, "flag": "-?", "long": "--help" }, { "name": "-V --version", "lines": 2, "flag": "-V", "long": "--version" }, { "name": "-c --copyright", "lines": 2, "flag": "-c", "long": "--copyright" }, { "name": "-v --verbose", "lines": 2, "flag": "-v", "long": "--verbose" }, { "name": "-i --icudatadir", "lines": 5, "flag": "-i", "long": "--icudatadir" }, { "name": "--uchars", "lines": 2, "long": "--uchars" }, { "name": "--bytes", "lines": 2, "long": "--bytes" }, { "name": "--transform", "lines": 7, "long": "--transform" }, { "name": "input-file", "lines": 2 }, { "name": "output-file", "lines": 2 } ] }, { "name": "CAVEATS", "lines": 4, "subsections": [] }, { "name": "ENVIRONMENT", "lines": 4, "subsections": [] }, { "name": "AUTHORS", "lines": 2, "subsections": [] }, { "name": "VERSION", "lines": 2, "subsections": [] }, { "name": "COPYRIGHT", "lines": 2, "subsections": [] }, { "name": "SEE ALSO", "lines": 1, "subsections": [ { "name": "http://www.icu-project.org/userguide/boundaryAnalysis.html", "lines": 1 } ] } ], "sections": { "NAME": { "content": "gendict - Compiles word list into ICU string trie dictionary\n", "subsections": [] }, "SYNOPSIS": { "content": "gendict [ --uchars | --bytes --transform transform ] [ -h, -?, --help ] [ -V, --version ] [", "subsections": [ { "name": "-c --copyright -v --verbose -i --icudatadir", "content": "", "flag": "-i", "long": "--icudatadir" } ] }, "DESCRIPTION": { "content": "gendict reads the word list from dictionary-file and creates a string trie dictionary file.\nNormally this data file has the .dict extension.\n\nWords begin at the beginning of a line and are terminated by the first whitespace. Lines\nthat begin with whitespace are ignored.\n", "subsections": [] }, "OPTIONS": { "content": "", "subsections": [ { "name": "-h -? --help", "content": "Print help about usage and exit.\n", "flag": "-?", "long": "--help" }, { "name": "-V --version", "content": "Print the version of gendict and exit.\n", "flag": "-V", "long": "--version" }, { "name": "-c --copyright", "content": "Embeds the standard ICU copyright into the output-file.\n", "flag": "-c", "long": "--copyright" }, { "name": "-v --verbose", "content": "Display extra informative messages during execution.\n", "flag": "-v", "long": "--verbose" }, { "name": "-i --icudatadir", "content": "Look for any necessary ICU data files in directory. For example, the file pnames.icu\nmust be located when ICU's data is not built as a shared library. The default ICU\ndata directory is specified by the environment variable ICUDATA. Most configurations\nof ICU do not require this argument.\n", "flag": "-i", "long": "--icudatadir" }, { "name": "--uchars", "content": "Set the output trie type to UChar. Mutually exclusive with --bytes.\n", "long": "--uchars" }, { "name": "--bytes", "content": "Set the output trie type to Bytes. Mutually exclusive with --uchars.\n", "long": "--bytes" }, { "name": "--transform", "content": "Set the transform type. Should only be specified with --bytes. Currently supported\ntransforms are: offset-, which specifies an offset to subtract from all\ninput characters. It should be noted that the offset transform also maps U+200D to\n0xFF and U+200C to 0xFE, in order to offer compatibility to languages that require\nthese characters. A transform must be specified for a bytes trie, and when applied to\nthe non-value characters in the input-file must produce output between 0x00 and 0xFF.\n", "long": "--transform" }, { "name": "input-file", "content": "The source file to read.\n" }, { "name": "output-file", "content": "The file to write the output dictionary to.\n" } ] }, "CAVEATS": { "content": "The input-file is assumed to be encoded in UTF-8. The integers in the input-file that are\nused as values must be made up of ASCII digits. They may be specified either in hex, by using\na 0x prefix, or in decimal. Either --bytes or --uchars must be specified.\n", "subsections": [] }, "ENVIRONMENT": { "content": "ICUDATA Specifies the directory containing ICU data. Defaults to ${prefix}/share/icu/70.1/.\nSome tools in ICU depend on the presence of the trailing slash. It is thus impor‐\ntant to make sure that it is present if ICUDATA is set.\n", "subsections": [] }, "AUTHORS": { "content": "Maxime Serrano\n", "subsections": [] }, "VERSION": { "content": "1.0\n", "subsections": [] }, "COPYRIGHT": { "content": "Copyright (C) 2012 International Business Machines Corporation and others\n", "subsections": [] }, "SEE ALSO": { "content": "", "subsections": [ { "name": "http://www.icu-project.org/userguide/boundaryAnalysis.html", "content": "ICU MANPAGE 1 June 2012 GENDICT(1)" } ] } } } }