{"count":52149,"next":"https://ports.macports.org/api/v1/ports/?ordering=updated_at&page=966","previous":"https://ports.macports.org/api/v1/ports/?ordering=updated_at&page=964","results":[{"name":"rman","portdir":"textproc/rman","version":"3.2","license":"Artistic-1","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://polyglotman.sourceforge.net/","description":"Man page format converter","long_description":"PolyglotMan takes formatted man pages from most of the popular flavours of UN*X and transforms them into any number of source formats. It can produce ASCII-only, section headers-only, TkMan, [tn]roff, Ensemble, SGML, HTML, LaTeX, RTF, Perl 5 POD.","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[{"type":"build","ports":["spim"]}]},{"name":"ripgrep-all","portdir":"textproc/ripgrep-all","version":"0.10.10","license":"AGPL","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/phiresky/ripgrep-all","description":"rga: ripgrep, but also search in PDFs, E-Books, Office documents, zip, tar.gz, etc.","long_description":"rga is a line-oriented search tool that allows you to look for a regex in a multitude of file types. rga wraps the awesome ripgrep and enables it to search in pdf, docx, sqlite, jpg, movie subtitles (mkv, mp4), etc.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]},{"type":"run","ports":["ripgrep"]}],"depends_on":[]},{"name":"rnnlm","portdir":"textproc/rnnlm","version":"0.4b","license":"Permissive","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://rnnlm.org","description":"Recurrent Neural Network Language Modeling Toolkit","long_description":"Neural network based language models are nowdays among the most successful techniques for statistical language modeling. They can be easily applied in wide range of tasks, including automatic speech recognition and machine translation, and provide significant improvements over classic backoff n-gram models.","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"roapi","portdir":"textproc/roapi","version":"0.13.0","license":"Apache-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://roapi.github.io/docs/","description":"Create full-fledged APIs for slowly moving datasets without writing a single line of code.","long_description":"ROAPI automatically spins up read-only APIs for static datasets without requiring you to write a single line of code. It builds on top of Apache Arrow and Datafusion. The core of its design can be boiled down to the following: - Query frontends to translate SQL, GraphQL and REST API queries into Datafusion plans. - Datafusion for query plan execution. - Data layer to load datasets from a variety of sources and formats with automatic schema inference. - Response encoding layer to serialize intermediate Arrow record batch into various formats requested by client.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","cmake","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"rpl","portdir":"textproc/rpl","version":"1.4.1","license":"Restrictive/Distributable","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://www.laffeycomputer.com/rpl.html","description":"Rpl is a Unix replacement utility","long_description":"rpl is a Unix text replacement utility. It will replace strings with new strings in multiple text files. It can scan directories recursively and replace strings in all files found. The search can be limited to files with certain filename suffixes (e.g. '.html', '.c', etc.).","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"rq","portdir":"textproc/rq","version":"1.0.4","license":"MIT","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/dflemstr/rq","description":"Record Query - A tool for doing record analysis and transformation","long_description":"rq is a tool that's used for performing queries on streams of records in various formats. The goal is to make ad-hoc exploration of data sets easy without having to use more heavy-weight tools like SQL/MapReduce/custom programs. rq fills a similar niche as tools like awk or sed, but works with structured (record) data instead of text. rq supports Apache Avro, CBOR, JSON, MessagePack, Google ProtoBuf, YAML, TOML, CSV, & plain text.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"columnq","portdir":"textproc/roapi","version":"0.10.0","license":"Apache-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/roapi/roapi","description":"Simple CLI to help you query tabular data with support for a rich set of growing formats and data sources.","long_description":"Simple CLI to help you query tabular data with support for a rich set of growing formats and data sources. It supports JSON, CSV, Parquet, Arrow and all other formats that are supported by ROAPI, which is documented at here. It also supports querying datasets from remote locations like S3 and HTTPs, see ROAPI's blob store documentation for more info.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","cmake","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"rtfreader","portdir":"textproc/rtfreader","version":"1.0","license":"unknown","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://www.fiction.net/blong/programs/#rtf","description":"Utility to read Microsoft RTF files","long_description":"RTF is the Microsoft Rich Text Format, a more portable, mostly ASCII formatting language that is exported by word processors like MS Word. The files generally have the extension .rtf, but occasionally have .doc extensions as well. This parser is from the Microsoft spec, ported to Unix systems.","active":true,"categories":["textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"rxp","portdir":"textproc/rxp","version":"1.4.8","license":"unknown","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://www.cogsci.ed.ac.uk/~richard/rxp.html","description":"Validating XML parser written in C.","long_description":"RXP is a validating XML parser written in C. The current version of RXP supports XML 1.1, Namespaces 1.1, xml:id, and XML Catalogs.","active":true,"categories":["textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"ruplacer","portdir":"textproc/ruplacer","version":"0.10.0","license":"BSD","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/dmerejkowsky/ruplacer","description":"Find and replace text in source files.","long_description":"Find and replace text in source files.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"sablotron","portdir":"textproc/sablotron","version":"1.0.3","license":"(MPL-1.1 or GPL-2+)","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sablotron.sourceforge.net/","description":"XSLT, DOM and XPath processor","long_description":"Sablotron is a fast, compact and portable XML toolkit implementing XSLT 1.0, DOM Level2 and XPath 1.0. Sablotron is an open project. The goal of this project is to create a lightweight, reliable and fast XML library processor conforming to the W3C specification, which is available for public and can be used as a base for multi-platform XML applications.","active":true,"categories":["textproc"],"maintainers":[],"variants":["apidocs","debugger","universal"],"dependencies":[{"type":"build","ports":["libtool","clang-18"]},{"type":"lib","ports":["spidermonkey","expat","libiconv"]}],"depends_on":[]},{"name":"sad","portdir":"textproc/sad","version":"0.4.32","license":"MIT","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/ms-jpq/sad","description":"Space Age seD - CLI Search And Replace","long_description":"Space Age seD - CLI Search And Replace","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]},{"type":"run","ports":["fzf"]}],"depends_on":[]},{"name":"sand","portdir":"textproc/sand","version":"0.3.0-20021016","license":"GPL-2+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sand.sourceforge.net/","description":"sand is a tool to help you keep your diary","long_description":"sand is a tool to help you keep your diary","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["autoconf","automake","libtool","texinfo","clang-18"]}],"depends_on":[]},{"name":"saxon","portdir":"textproc/saxon","version":"9.5.1.1","license":"MPL-1","platforms":"any","epoch":0,"replaced_by":null,"homepage":"http://saxon.sourceforge.net/","description":"saxon home edition - collection of tools to process XML documents","long_description":"Saxon-HE provides implementations of XSLT 2.0, XQuery 1.0, and XPath 2.0 at the basic level of conformance defined by W3C.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["kaffe"]}],"depends_on":[]},{"name":"scdoc","portdir":"textproc/scdoc","version":"1.11.4","license":"MIT","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://git.sr.ht/~sircmpwn/scdoc","description":"Simple man page generator.","long_description":"scdoc is a simple man page generator for POSIX systems written in C99.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[{"type":"build","ports":["alacritty","hut","shfmt","smithy","cbonsai","senpai","aerc","astroid","maddy","age-plugin-se","nvimpager","ijq","kiln"]}]},{"name":"sd","portdir":"textproc/sd","version":"1.1.0","license":"MIT","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/chmln/sd","description":"Intuitive find & replace CLI (sed alternative)","long_description":"Intuitive find & replace CLI (sed alternative). sd uses regex syntax that you already know from JavaScript and Python. Forget about dealing with quirks of sed or awk - get productive immediately.","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"sdcv","portdir":"textproc/sdcv","version":"0.5.5","license":"GPL-2+","platforms":"darwin","epoch":1,"replaced_by":null,"homepage":"https://dushistov.github.io/sdcv/","description":"console version of StarDict program","long_description":"sdcv is a console version of the StarDict program.","active":true,"categories":["textproc"],"maintainers":[{"name":"ryandesign","github":"ryandesign","ports_count":2085}],"variants":["debug","universal"],"dependencies":[{"type":"build","ports":["cmake","pkgconfig","clang-18"]},{"type":"lib","ports":["zlib","readline","gettext","glib2"]}],"depends_on":[]},{"name":"seekanser","portdir":"textproc/seekanser","version":"1.0.7","license":"LGPL-3","platforms":"any","epoch":0,"replaced_by":null,"homepage":"http://seekanser.sourceforge.jp/","description":"a program to seek answers to a quiz in Japanese","long_description":"SeekAnser is a program to seek answers to a quiz in Japanese.","active":true,"categories":["textproc","java","japanese"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["chasen"]}],"depends_on":[]},{"name":"senna","portdir":"textproc/senna","version":"1.1.4","license":"unknown","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://qwik.jp/senna/","description":"embeddable fulltext search engine","long_description":"Senna is an embeddable fulltext search engine, which you can use in conjunction with various scripting languages and databases.","active":true,"categories":["textproc"],"maintainers":[{"name":"hello","github":"","ports_count":1}],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"lib","ports":["mecab","mecab-ipadic-utf8"]}],"depends_on":[]},{"name":"sentencepiece","portdir":"textproc/sentencepiece","version":"0.2.1","license":"Apache-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/google/sentencepiece","description":"Unsupervised text tokenizer for Neural Network-based text generation.","long_description":"SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece implements subword units (e.g., byte-pair-encoding (BPE) (Sennrich et al.) and unigram language model (Kudo)) with the extension of direct training from raw sentences. SentencePiece allows us to make a purely end-to-end system that does not depend on language-specific pre/postprocessing.","active":true,"categories":["textproc"],"maintainers":[],"variants":["debug","universal"],"dependencies":[{"type":"build","ports":["cmake","clang-20"]},{"type":"lib","ports":["protobuf3-cpp"]}],"depends_on":[{"type":"lib","ports":["py37-sentencepiece","py38-sentencepiece","py39-sentencepiece","py310-sentencepiece","py311-sentencepiece","py312-sentencepiece","py313-sentencepiece","py314-sentencepiece"]}]},{"name":"sgml-common","portdir":"textproc/sgml-common","version":"0.6.3","license":"GPL-2+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"http://www.w3.org/2003/entities/","description":"A collection of entities and DTDs common to multiple packages.","long_description":"The sgml-common package contains a collection of entities and DTDs that are useful for processing SGML, but that don't need to be included in multiple packages. Sgml-common also includes an up-to-date Open Catalog file. Transcribed from the Fedora 15 RPM written originally by Tim Waugh <twaugh@redhat.com> based on work by Eric Bischoff and with recent maintenance by Ondrej Vasik <ovasik@redhat.com>.","active":true,"categories":["textproc"],"maintainers":[{"name":"tlockhart1976","github":"lockhart","ports_count":27}],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"lib","ports":["perl5","libxml2","xmlcatmgr"]}],"depends_on":[{"type":"lib","ports":["docbook-utils"]}]},{"name":"sgrep","portdir":"textproc/sgrep","version":"0.99","license":"GPL-2+","platforms":"darwin","epoch":1,"replaced_by":null,"homepage":"http://www.cs.helsinki.fi/u/jjaakkol/sgrep.html","description":"structured grep is a tool for searching SGML, XML and HTML files","long_description":"sgrep (structured grep) is a tool for searching and indexing text, SGML, XML and HTML files and filtering text streams using structural criteria.","active":true,"categories":["textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"sgrep2","portdir":"textproc/sgrep2","version":"1.94a","license":"unknown","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://www.cs.helsinki.fi/u/jjaakkol/sgrep.html","description":"structured grep is a tool for searching SGML, XML and HTML files","long_description":"sgrep (structured grep) is a tool for searching and indexing text, SGML, XML and HTML files and filtering text streams using structural criteria.","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["automake","clang-18"]}],"depends_on":[]},{"name":"simstring","portdir":"textproc/simstring","version":"20140723","license":"BSD","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://www.chokkan.org/software/simstring/","description":"A fast and simple algorithm for approximate string matching/retrieval","long_description":"SimString is a simple library for fast approximate string retrieval. Approximate string retrieval finds strings in a database whose similarity with a query string is no smaller than a threshold. Finding not only identical but similar strings, approximate string retrieval has various applications including spelling correction, flexible dictionary matching, duplicate detection, and record linkage.","active":true,"categories":["textproc","math"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["autoconf","automake","libtool","clang-18"]}],"depends_on":[]},{"name":"sig","portdir":"textproc/sig","version":"0.3.0","license":"MIT","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://github.com/ynqa/sig","description":"Interactive grep (for streaming)","long_description":"Interactive grep (for streaming)","active":true,"categories":["textproc"],"maintainers":[{"name":"herby.gillot","github":"herbygillot","ports_count":1063}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"slearp","portdir":"textproc/slearp","version":"0.95","license":"GPL-3","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sourceforge.jp/projects/slearp/","description":"structured learning and predict toolkit for tasks such as g2p conversion, based on discriminative leaning","long_description":"Slearp (structured learning and prediction) is the structured learning and predict toolkit for tasks such as g2p conversion, based on discriminative leaning.","active":true,"categories":["textproc","math"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"py27-simstring","portdir":"textproc/simstring","version":"20140723","license":"BSD","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://www.chokkan.org/software/simstring/","description":"SimString Python module","long_description":"SimString Python module","active":true,"categories":["textproc","math","python"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["autoconf","automake","libtool","swig-python","clang-18"]},{"type":"lib","ports":["python27"]}],"depends_on":[]},{"name":"sloccount","portdir":"textproc/sloccount","version":"2.26","license":"GPL-2+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://dwheeler.com/sloccount/","description":"program for counting lines of code in a large number of languages","long_description":"SLOCCount is a set of tools for counting physical Source Lines of Code (SLOC) in a large number of languages of a potentially large set of programs.","active":true,"categories":["devel","textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"run","ports":["perl5","bash"]}],"depends_on":[]},{"name":"source-highlight","portdir":"textproc/source-highlight","version":"3.1.9","license":"GPL-3+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://www.gnu.org/software/src-highlite/","description":"source-code syntax highlighter","long_description":"This program, given a source file, produces a document with syntax highlighting. At the moment it can handle: C/C++, C#, Bib, Bison, Caml, Changelog, CSS, Diff, Flex, Fortran, Html, Java, Javascript, Latex, Logtalk, Log files, Lua, Makefile, M4, ML, Pascal, Perl, PHP, PostScript, Prolog, Python, Ruby, Shell, Sql, Tcl, and XML.","active":true,"categories":["devel","textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["autoconf","automake","libtool","clang-18"]},{"type":"lib","ports":["ctags","boost176"]}],"depends_on":[]},{"name":"sowing","portdir":"textproc/sowing","version":"1.1.25","license":"GPL-2+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://mcs.anl.gov","description":"A parser for fortran interfaces","long_description":"A parser for fortran interfaces","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[{"type":"build","ports":["petsc","slepc"]}]},{"name":"spark","portdir":"textproc/spark","version":"1.0.1","license":"MIT","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://github.com/holman/spark","description":"sparklines for your shell.","long_description":"spark: sparklines for your shell.","active":true,"categories":["textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"sphinx","portdir":"textproc/sphinx","version":"2.2.11","license":"GPL-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sphinxsearch.com/","description":"Sphinx is a full-text search engine","long_description":"Sphinx is a full-text search engine, meant to provide fast, size-efficient and relevant fulltext search functions to other applications. Sphinx was specially designed to integrate well with SQL databases and scripting languages. Currently built-in data sources support fetching data either via direct connection to MySQL or PostgreSQL, or from an XML pipe.","active":true,"categories":["net","textproc"],"maintainers":[],"variants":["postgresql91","postgresql92","postgresql93","postgresql94","postgresql95","postgresql96","mysql51","mysql55","mysql56","mysql57","mariadb","universal"],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"lib","ports":["mysql57","expat","libiconv"]}],"depends_on":[{"type":"build","ports":["iverilog-docs"]}]},{"name":"ssed","portdir":"textproc/ssed","version":"3.62","license":"GPL-2+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sed.sourceforge.net/","description":"Super-sed - a heavily enhanced version of sed","long_description":"This is a version of sed based on GNU sed. It is not a version of GNU sed, though. There are several new features (including in-place editing of files, extended regular expression syntax and a few new commands) and some bug fixes.","active":true,"categories":["textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"lib","ports":["gettext","libiconv"]}],"depends_on":[]},{"name":"libsphinxclient","portdir":"textproc/sphinx","version":"2.2.11","license":"LGPL-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://sphinxsearch.com/","description":"C library to talk to the Sphinx full-text search engine","long_description":"C library to talk to the Sphinx full-text search engine","active":true,"categories":["net","textproc"],"maintainers":[],"variants":["universal"],"dependencies":[{"type":"build","ports":["autoconf","automake","libtool","clang-18"]}],"depends_on":[{"type":"lib","ports":["php53-sphinx","php54-sphinx","php55-sphinx","php56-sphinx"]}]},{"name":"stanford-corenlp","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["apache-ant","openjdk11"]},{"type":"run","ports":["stanford-corenlp-models"]}],"depends_on":[{"type":"run","ports":["py27-stanfordnlp","py38-stanfordnlp","py37-stanfordnlp","stanford-corenlp-arabic","stanford-corenlp-chinese","stanford-corenlp-english","stanford-corenlp-english-kbp","stanford-corenlp-french","stanford-corenlp-german","stanford-corenlp-spanish"]}]},{"name":"stanford-ner","portdir":"textproc/stanford-ner","version":"4.2.0","license":"GPL-2+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://nlp.stanford.edu/software/CRF-NER.shtml","description":"a high-performance machine learning based named entity recognition system","long_description":"a high-performance machine learning based named entity recognition system, including facilities to train models from supervised training data and pre-trained models for English.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]}],"depends_on":[]},{"name":"stanford-corenlp-models","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]}],"depends_on":[{"type":"run","ports":["stanford-corenlp","stanford-corenlp-arabic","stanford-corenlp-chinese","stanford-corenlp-english","stanford-corenlp-english-kbp","stanford-corenlp-french","stanford-corenlp-german","stanford-corenlp-spanish"]}]},{"name":"stanford-corenlp-arabic","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-chinese","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-english","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-english-kbp","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-french","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-german","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-corenlp-spanish","portdir":"textproc/stanford-corenlp","version":"3.9.2","license":"GPL-3+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://stanfordnlp.github.io/CoreNLP/","description":"A Java suite of core NLP tools","long_description":"Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize and interpret dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases or word dependencies, and indicate which noun phrases refer to the same entities. It was originally developed for English, but now also provides varying levels of support for (Modern Standard) Arabic, (mainland) Chinese, French, German, and Spanish. Stanford CoreNLP is an integrated framework, which makes it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications. Stanford CoreNLP is a set of stable and well-tested natural language processing tools, widely used by various groups in academia, industry, and government. The tools variously use rule-based, probabilistic machine learning, and deep learning components.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]},{"type":"lib","ports":["openjdk11"]},{"type":"run","ports":["stanford-corenlp","stanford-corenlp-models"]}],"depends_on":[]},{"name":"stanford-parser","portdir":"textproc/stanford-parser","version":"4.2.0","license":"GPL-2+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://nlp.stanford.edu/software/lex-parser.html","description":"a Java implementation of probabilistic natural language parsers","long_description":"a Java implementation of probabilistic natural language parsers, both highly optimized PCFG and lexicalized dependency parsers, and a lexicalized PCFG parser.","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]}],"depends_on":[]},{"name":"stanford-postagger","portdir":"textproc/stanford-postagger","version":"4.2.0","license":"GPL-2+","platforms":"any","epoch":0,"replaced_by":null,"homepage":"https://nlp.stanford.edu/software/tagger.html","description":"a Java implementation of the log-linear part-of-speech taggers","long_description":"a Java implementation of the log-linear part-of-speech taggers","active":true,"categories":["textproc","java"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"extract","ports":["unzip"]}],"depends_on":[]},{"name":"stardict","portdir":"textproc/stardict","version":"3.0.7","license":"GPL-3+","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"http://stardict-4.sourceforge.net/index_en.php","description":"A full featured gtk2 dictionary","long_description":"Very nice gnome dictionary. Can handle both local and web dictionaries. Though it needs a handful of gnome libraries for installation.","active":true,"categories":["textproc"],"maintainers":[{"name":"alexandernx","github":"","ports_count":2}],"variants":["gnome","universal"],"dependencies":[{"type":"build","ports":["gnome-common","clang-18","itstool","intltool","yelp-tools","gnome-doc-utils","autoconf","automake","libtool","pkgconfig","gconf"]},{"type":"extract","ports":["p7zip"]},{"type":"lib","ports":["gtk3","libsigcxx2","json-glib","glib2","libcanberra","espeak-ng"]}],"depends_on":[]},{"name":"stardict-xmlittre","portdir":"textproc/stardict-xmlittre","version":"2.4.2","license":"unknown","platforms":"any","epoch":0,"replaced_by":null,"homepage":"http://francois.gannaz.free.fr/Littre/accueil.php","description":"XMLittré dictionary for stardict","long_description":"XMLittré dictionary for stardict.","active":true,"categories":["textproc"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]}],"depends_on":[]},{"name":"stork","portdir":"textproc/stork","version":"1.5.0","license":"Apache-2","platforms":"darwin","epoch":0,"replaced_by":null,"homepage":"https://stork-search.net/","description":"Impossibly fast web search, made for static sites.","long_description":"Stork is a library for creating beautiful, fast, and accurate full-text search interfaces on the web.","active":true,"categories":["textproc","www"],"maintainers":[{"name":"jobrien_stork","github":"neirbowj","ports_count":1}],"variants":["universal"],"dependencies":[{"type":"build","ports":["cargo","legacy-support","rust","clang-20"]},{"type":"lib","ports":["libunwind"]}],"depends_on":[]},{"name":"string_replace","portdir":"textproc/string_replace","version":"0.1","license":"GPL-2","platforms":"any","epoch":0,"replaced_by":null,"homepage":"http://freecode.com/projects/string_replace","description":"searches and replaces a text string or regular expression","long_description":"This tool was designed to go through text files (meaning: text, html, php, etc.) to search for and replace a particular text string (or regular expression).","active":true,"categories":["textproc","perl"],"maintainers":[],"variants":[],"dependencies":[{"type":"build","ports":["clang-18"]},{"type":"run","ports":["perl5"]}],"depends_on":[]}]}