codemeta.json

{
    "@context": [
        "https://doi.org/10.5063/schema/codemeta-2.0",
        "http://schema.org",
        {
            "entryPoints": { "@reverse": "schema:actionApplication" },
            "interfaceType": { "@id": "codemeta:interfaceType" }
        }
    ],
    "@type": "SoftwareSourceCode",
    "identifier": "ticcltools",
    "name": "TICCLTools",
    "version": "0.11",
    "description": "TicclTools is a collection of programs to process datafiles, together they constitute the bulk of TICCL: Text Induced Corpus-Cleanup. This software consists of individual modules that are invoked by the pipeline system PICCL.",
    "license": "https://spdx.org/licenses/GPL-3.0",
	"url": "https://github.com/LanguageMachines/ticcltools",
    "author": [
		{
			"@type": "Person",
			"givenName": "Martin",
			"familyName": "Reynaert",
			"email": "reynaert@uvt.nl",
			"affiliation": {
				"@id": "https://www.ru.nl/clst",
				"@type": "Organization",
				"name": "Centre for Language and Speech Technology",
				"url": "https://www.ru.nl/clst",
				"parentOrganization": {
					"@id": "https://www.ru.nl/cls",
					"@type": "Organization",
					"name": "Centre for Language Studies",
					"url": "https://www.ru.nl/cls",
					"parentOrganization": {
						"@id": "https://www.ru.nl",
						"name": "Radboud University",
						"@type": "Organization",
						"url": "https://www.ru.nl",
						"location": {
							"@type": "Place",
							"name": "Nijmegen"
						}
					}

				}
			}
		},
		{
			"@type": "Person",
			"givenName": "Ko",
			"familyName": "van der Sloot",
			"email": "k.vandersloot@let.ru.nl",
			"affiliation": { "@id": "https://www.ru.nl/clst" }
		}
	],
	"sourceOrganization": { "@id": "https://www.ru.nl/clst" },
	"programmingLanguage": {
		"@type": "ComputerLanguage",
		"identifier": "c++",
		"name": "C++"
	},
	"operatingSystem": "POSIX",
	"codeRepository": "https://github.com/LanguageMachines/ticcltools",
    "softwareRequirements": [
        {
			"@type": "SoftwareApplication",
			"identifier": "ticcutils",
			"name": "Ticcutils"
		}
	],
	"funder": [
		{
			"@type": "Organization",
			"name": "CLARIN-NL"
		},
		{
			"@type": "Organization",
			"name": "CLARIAH",
			"url": "https://www.clariah.nl"
		}
	],
	"readme": "https://github.com/LanguageMachines/ticcltools/blob/master/README.md",
	"issueTracker": "https://github.com/LanguageMachines/ticcltools/issues",
	"contIntegration": "https://travis-ci.org/LanguageMachines/ticcltools",
	"releaseNotes": "https://github.com/LanguageMachines/ticcltools/releases",
	"developmentStatus": "unsupported",
	"keywords":  [ "nlp", "natural language processing", "ocr", "normalization" ],
    "referencePublication": [
		{
			"@type": "ScholarlyArticle",
			"name": "PICCL: Philosophical Integrator of Computational and Corpus Libraries",
			"author": [ "Martin Reynaert", "Maarten van Gompel", "Ko van der Sloot", "Antal van den Bosch" ],
			"pageStart": "75",
			"pageEnd": 79,
			"isPartOf": {
				"@type": "PublicationIssue",
				"datePublised": "2015",
				"name": "Proceedings of CLARIN Annual Conference 2015",
				"location": "Wrocław, Poland"
			},
            "url": "http://www.nederlab.nl/cms/wp-content/uploads/2015/10/Reynaert_PICCL-Philosophical-Integrator-of-Computational-and-Corpus-Libraries.pdf"
		}
	],
	"dateCreated": "2015",
    "entryPoints": [
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-indexer",
            "name": "TICCL-indexer",
            "description": "A tool to create an exhaustive index to all lexical variants given a particular Levenshtein or edit distance in a corpus.",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-indexerNT",
            "name": "TICCL-indexerNT",
            "description": "A tool to create an exhaustive index to all lexical variants given a particular Levenshtein or edit distance in a corpus.",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-anahash",
            "name": "TICCL-anahash",
            "description": "A tool to create anagram hashes from a word frequency file. Also creates a 'alphabet' file of the unicode characters that are present in the corpus.",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-LDcalc",
            "name": "TICCL-LDcalc",
            "description": "A pre-processing tool for TICCL-rank. Gathers the info from TICC-anahash, TICCL-indexer, TICCL-lexstat and TICCL-unk",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-rank",
            "name": "TICCL-rank",
            "description": "ranks a word varian list according to a lot of criteria",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-unk",
            "name": "TICCL-unk",
            "description": "a cleanup tool for word frequency lists. creates a 'clean' file with desirable words, an 'unk' file with uncorrectable words and a 'punct' file with words that would be clean after removing puncuation.",
            "interfaceType": "CLI"
        },
        {
            "@type": "EntryPoint",
            "urlTemplate": "file:///TICCL-lexstat",
            "name": "TICCL-lexstat",
            "description": "convert an 'alphabet' file (from TICCL-anahash) into a frequency list of hashes and optionally a list of confusions.",
            "interfaceType": "CLI"
        }
    ]
}