1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2015 Taylan Ulrich Bayırlı/Kammer <taylanbayirli@gmail.com>
3 ;;; Copyright © 2015, 2016, 2017, 2018, 2019, 2020 Ricardo Wurmus <rekado@elephly.net>
4 ;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
5 ;;; Copyright © 2015 Roel Janssen <roel@gnu.org>
6 ;;; Copyright © 2016 Jelle Licht <jlicht@fsfe.org>
7 ;;; Copyright © 2016 Alex Griffin <a@ajgrf.com>
8 ;;; Copyright © 2016, 2018, 2019, 2020 Efraim Flashner <efraim@flashner.co.il>
9 ;;; Copyright © 2016 Nikita <nikita@n0.is>
10 ;;; Copyright © 2016, 2020 Marius Bakke <marius@gnu.org>
11 ;;; Copyright © 2017 Eric Bavier <bavier@member.fsf.org>
12 ;;; Copyright © 2017 Rene Saavedra <rennes@openmailbox.org>
13 ;;; Copyright © 2017,2019 Hartmut Goebel <h.goebel@crazy-compilers.com>
14 ;;; Copyright © 2017 Kei Kebreau <kkebreau@posteo.net>
15 ;;; Copyright © 2017 Alex Vong <alexvong1995@gmail.com>
16 ;;; Copyright © 2018, 2019, 2020 Tobias Geerinckx-Rice <me@tobias.gr>
17 ;;; Copyright © 2018 Pierre Neidhardt <mail@ambrevar.xyz>
18 ;;; Copyright © 2018 Meiyo Peng <meiyo.peng@gmail.com>
19 ;;; Copyright © 2019 Yoshinori Arai <kumagusu08@gmail.com>
20 ;;; Copyright © 2019 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
21 ;;; Copyright © 2019 Wiktor Żelazny <wzelazny@vurv.cz>
22 ;;; Copyright © 2020 Maxim Cournoyer <maxim.cournoyer@gmail.com>
24 ;;; This file is part of GNU Guix.
26 ;;; GNU Guix is free software; you can redistribute it and/or modify it
27 ;;; under the terms of the GNU General Public License as published by
28 ;;; the Free Software Foundation; either version 3 of the License, or (at
29 ;;; your option) any later version.
31 ;;; GNU Guix is distributed in the hope that it will be useful, but
32 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
33 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
34 ;;; GNU General Public License for more details.
36 ;;; You should have received a copy of the GNU General Public License
37 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
39 (define-module (gnu packages textutils)
40 #:use-module ((guix licenses) #:prefix license:)
41 #:use-module (guix packages)
42 #:use-module (guix download)
43 #:use-module (guix git-download)
44 #:use-module (guix build-system ant)
45 #:use-module (guix build-system gnu)
46 #:use-module (guix build-system go)
47 #:use-module (guix build-system cmake)
48 #:use-module (guix build-system python)
49 #:use-module (guix utils)
50 #:use-module (gnu packages)
51 #:use-module (gnu packages autotools)
52 #:use-module (gnu packages base)
53 #:use-module (gnu packages compression)
54 #:use-module (gnu packages gcc)
55 #:use-module (gnu packages golang)
56 #:use-module (gnu packages gettext)
57 #:use-module (gnu packages java)
58 #:use-module (gnu packages ncurses)
59 #:use-module (gnu packages pcre)
60 #:use-module (gnu packages perl)
61 #:use-module (gnu packages pkg-config)
62 #:use-module (gnu packages python)
63 #:use-module (gnu packages python-xyz)
64 #:use-module (gnu packages readline)
65 #:use-module (gnu packages slang)
66 #:use-module (gnu packages web))
68 (define-public dos2unix
75 (uri (string-append "https://waterlan.home.xs4all.nl/dos2unix/"
76 "dos2unix-" version ".tar.gz"))
78 (base32 "00dfsf4rfyjb5j12gan8xjiirm0asshdz6dmd3l34a7ays6wadb0"))))
79 (build-system gnu-build-system)
82 (list (string-append "CC=" ,(cc-for-target))
83 (string-append "prefix=" (assoc-ref %outputs "out")))
85 (modify-phases %standard-phases
86 (delete 'configure)))) ; no configure script
88 `(("gettext" ,gettext-minimal)
90 (home-page "https://waterlan.home.xs4all.nl/dos2unix.html")
91 (synopsis "DOS/Mac to Unix and vice versa text file format converter")
93 "dos2unix is a tool to convert line breaks in a text file from Unix format
94 to DOS format and vice versa.")
95 (license license:bsd-2)))
104 (uri (string-append "https://github.com/rrthomas/recode/releases/"
105 "download/v" version "/recode-" version ".tar.gz"))
107 (base32 "0m59sd1ca0zw1aydpc3m8sw03nc885knmccqryg7byzmqs585ia6"))))
108 (build-system gnu-build-system)
111 ("python-cython" ,python-cython)))
112 (home-page "https://github.com/rrthomas/recode")
113 (synopsis "Text encoding converter")
114 (description "The Recode library converts files between character sets and
115 usages. It recognises or produces over 200 different character sets (or about
116 300 if combined with an iconv library) and transliterates files between almost
117 any pair. When exact transliteration are not possible, it gets rid of
118 offending characters or falls back on approximations. The recode program is a
119 handy front-end to the library.")
120 (license license:gpl3+)))
130 (url "https://github.com/nijel/enca")
132 (file-name (git-file-name name version))
134 (base32 "19q7cwwxmmk5j9438bsqdpjvdjawsd3zmw1zyqgi7s4m0rasr3ah"))))
135 (build-system gnu-build-system)
136 ;; enca-1.19 tests fail with recent recode.
137 ;(inputs `(("recode" ,recode)))
138 (home-page "https://github.com/nijel/enca")
139 (synopsis "Text encoding detection tool")
140 (description "Enca (Extremely Naive Charset Analyser) consists of libenca,
141 an encoding detection library, and enca, a command line frontend, integrating
142 libenca and several charset conversion libraries and tools.")
143 (license license:gpl2)))
145 (define-public utf8proc
153 (url "https://github.com/JuliaStrings/utf8proc")
154 (commit (string-append "v" version))))
155 (file-name (git-file-name name version))
157 (base32 "1xlkazhdnja4lksn5c9nf4bln5gjqa35a8gwlam5r0728w0h83qq"))))
158 (build-system gnu-build-system)
160 (let ((UNICODE_VERSION "13.0.0")) ; defined in data/Makefile
161 ;; Test data that is otherwise downloaded with curl.
162 `(("NormalizationTest.txt"
165 (uri (string-append "https://www.unicode.org/Public/"
166 UNICODE_VERSION "/ucd/NormalizationTest.txt"))
168 (base32 "07g0ya4f6zfzvpp24ccxkb2yq568kh83gls85rjl950nv5fya3nn"))))
169 ("GraphemeBreakTest.txt"
172 (uri (string-append "https://www.unicode.org/Public/"
174 "/ucd/auxiliary/GraphemeBreakTest.txt"))
176 (base32 "07f8rrvcsq4pibdz6zxggxy8w7zjjqyw2ggclqlhalyv45yv7prj"))))
181 '(#:make-flags (list "CC=gcc"
182 (string-append "prefix=" (assoc-ref %outputs "out")))
184 (modify-phases %standard-phases
186 (add-before 'check 'check-data
187 (lambda* (#:key inputs #:allow-other-keys)
188 (for-each (lambda (i)
189 (copy-file (assoc-ref inputs i)
190 (string-append "data/" i)))
191 '("NormalizationTest.txt" "GraphemeBreakTest.txt"))
192 (substitute* "data/GraphemeBreakTest.txt"
196 (home-page "https://juliastrings.github.io/utf8proc/")
197 (synopsis "C library for processing UTF-8 Unicode data")
198 (description "utf8proc is a small C library that provides Unicode
199 normalization, case-folding, and other operations for data in the UTF-8
200 encoding, supporting Unicode version 9.0.0.")
201 (license license:expat)))
203 (define-public libconfuse
210 (uri (string-append "https://github.com/martinh/libconfuse/"
211 "releases/download/v" version
212 "/confuse-" version ".tar.xz"))
214 (base32 "043hqqykpprgrkw9s2hbdlxr308a7yxwsgxj4m8aadg1401hmm8x"))))
215 (build-system gnu-build-system)
217 '(#:configure-flags '("--disable-static")))
218 (home-page "https://github.com/martinh/libconfuse")
219 (synopsis "Configuration file parser library")
220 (description "libconfuse is a configuration file parser library. It
221 supports sections and (lists of) values (strings, integers, floats, booleans
222 or other sections), as well as some other features (such as
223 single/double-quoted strings, environment variable expansion, functions and
224 nested include statements).")
225 (license license:isc)))
227 (define-public libgtextutils
229 (name "libgtextutils")
235 "https://github.com/agordon/libgtextutils/releases/download/"
236 version "/libgtextutils-" version ".tar.gz"))
238 (base32 "0jiybkb2z58wa2msvllnphr4js2hvjvh988pavb3mzkgr6ihwbkr"))))
239 (build-system gnu-build-system)
242 (modify-phases %standard-phases
244 (lambda _ (invoke "sh" "reconf")))
245 (add-after 'set-paths 'hide-default-gcc
246 (lambda* (#:key inputs #:allow-other-keys)
247 (let ((gcc (assoc-ref inputs "gcc")))
248 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
249 ;; conflicts with the GCC 5 input.
250 (setenv "CPLUS_INCLUDE_PATH"
252 (delete (string-append gcc "/include/c++")
253 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
257 `(("autoconf" ,autoconf)
258 ("automake" ,automake)
259 ("gcc@5" ,gcc-5) ; doesn't build with later versions
260 ("libtool" ,libtool)))
261 (home-page "https://github.com/agordon/libgtextutils")
262 (synopsis "Gordon's text utils library")
264 "libgtextutils is a text utilities library used by the fastx toolkit from
266 (license license:agpl3+)))
268 (define-public cityhash
269 (let ((commit "8af9b8c"))
272 (version (string-append "1.1-2." commit))
276 (url "https://github.com/google/cityhash")
278 (file-name (string-append name "-" version ".tar.gz"))
281 "0n6skf5dv8yfl1ckax8dqhvsbslkwc9158zf2ims0xqdvzsahbi6"))))
282 (build-system gnu-build-system)
284 '(#:make-flags (list "CXXFLAGS=-g -O3")
286 (modify-phases %standard-phases
287 ;; citycrc is not installed by default but is used by some
289 (add-after 'install 'install-citycrc
290 (lambda* (#:key outputs #:allow-other-keys)
291 (let* ((out (assoc-ref outputs "out"))
292 (include (string-append out "/include")))
293 (install-file "src/citycrc.h" include))
295 (home-page "https://github.com/google/cityhash")
296 (synopsis "C++ hash functions for strings")
298 "CityHash provides hash functions for strings. The functions mix the
299 input bits thoroughly but are not suitable for cryptography.")
300 (license license:expat))))
308 (uri (string-append "http://www.and.org/ustr/" version
309 "/ustr-" version ".tar.bz2"))
312 "1i623ygdj7rkizj7985q9d6vj5amwg686aqb5j3ixpkqkyp6xbrx"))
313 (patches (search-patches "ustr-fix-build-with-gcc-5.patch"))))
314 (build-system gnu-build-system)
319 ;; Override "/sbin/ldconfig" with "echo" because we don't need
322 (string-append "prefix=" (assoc-ref %outputs "out"))
325 (modify-phases %standard-phases
326 (add-after 'unpack 'disable-check-for-stdint
328 ;; Of course we have stdint.h, just not in /usr/include
329 (substitute* '("Makefile"
331 (("-f \"/usr/include/stdint.h\"") "-z \"\""))
333 ;; No configure script
334 (delete 'configure))))
335 (home-page "http://www.and.org/ustr/")
336 (synopsis "String library with very low memory overhead")
338 "Ustr is a string library for C with very low memory overhead.")
339 ;; Quoted from the home page: "The License for the code is MIT, new-BSD,
340 ;; LGPL, etc. ... if you need another license to help compatibility, just
341 ;; ask for it. It's basically public domain, without all the legal
342 ;; problems for everyone that trying to make something public domain
344 (license license:public-domain)))
346 (define-public ascii2binary
348 (name "ascii2binary")
353 (uri (string-append "http://billposer.org/Software/Downloads/"
354 "ascii2binary-" version ".tar.bz2"))
356 (base32 "0dc9fxcdmppbs9s06jvq61zbk552laxps0xyk098gj41697ihd96"))))
357 (build-system gnu-build-system)
359 `(("gettext" ,gettext-minimal)))
360 (home-page "https://billposer.org/Software/a2b.html")
361 (synopsis "Convert between ASCII, hexadecimal and binary representations")
362 (description "The two programs are useful for generating test data, for
363 inspecting binary files, and for interfacing programs that generate textual
364 output to programs that require binary input and conversely. They can also be
365 useful when it is desired to reformat numbers.
369 @item @command{ascii2binary} reads input consisting of ascii or hexadecimal
370 representation numbers separated by whitespace and produces as output
371 the binary equivalents. The type and precision of the binary output
372 is selected using command line flags.
374 @item @command{binary2ascii} reads input consisting of binary numbers
375 and converts them to their ascii or hexadecimal representation.
376 Command line flags specify the type and size of the binary numbers
377 and provide control over the format of the output.
378 Unsigned integers may be written out in binary, octal, decimal,
381 Signed integers may be written out only in binary or decimal. Floating
382 point numbers may be written out only decimal, either in standard or
383 scientific notation. (If you want to examine the binary representation
384 of floating point numbers, just treat the input as a sequence of unsigned
388 (license license:gpl3)))
390 (define-public uniutils
397 (uri (string-append "http://billposer.org/Software/Downloads/"
398 "uniutils-" version ".tar.bz2"))
400 (base32 "19w1510w87gx7n4qy3zsb0m467a4rn5scvh4ajajg7jh6x5xri08"))))
401 (build-system gnu-build-system)
403 '(#:configure-flags '("--disable-dependency-tracking")
405 (modify-phases %standard-phases
406 (add-after 'build 'fix-paths
407 (lambda* (#:key outputs inputs #:allow-other-keys)
408 (let ((out (assoc-ref outputs "out"))
409 (a2b (assoc-ref inputs "ascii2binary"))
410 (iconv (assoc-ref inputs "libiconv")))
411 (substitute* "utf8lookup"
412 (("^ascii2binary ") (string-append a2b "/bin/ascii2binary "))
413 (("^uniname ") (string-append out "/bin/uniname "))
414 (("^iconv ") (string-append iconv "/bin/iconv ")))
417 `(("ascii2binary" ,ascii2binary)
418 ("libiconv" ,libiconv)))
419 (home-page "https://billposer.org/Software/unidesc.html")
420 (synopsis "Find out what is in a Unicode file")
421 (description "Useful tools when working with Unicode files when one
422 doesn't know the writing system, doesn't have the necessary font, needs to
423 inspect invisible characters, needs to find out whether characters have been
424 combined or in what order they occur, or needs statistics on which characters
429 @item @command{uniname} defaults to printing the character offset of each
430 character, its byte offset, its hex code value, its encoding, the glyph
431 itself, and its name. It may also be used to validate UTF-8 input.
433 @item @command{unidesc} reports the character ranges to which different
434 portions of the text belong. It can also be used to identify Unicode encodings
435 (e.g. UTF-16be) flagged by magic numbers.
437 @item @command{unihist} generates a histogram of the characters in its input.
439 @item @command{ExplicateUTF8} is intended for debugging or for learning about
440 Unicode. It determines and explains the validity of a sequence of bytes as a
443 @item @command{utf8lookup} provides a handy way to look up Unicode characters
444 from the command line.
446 @item @command{unireverse} reverse each line of UTF-8 input
447 character-by-character.
450 (license license:gpl3)))
452 (define-public libconfig
456 (home-page "https://hyperrealm.github.io/libconfig/")
459 (uri (string-append home-page "/dist/libconfig-"
463 "1ngs2qx3cx5cbwinc5mvadly0b5n7s86zsc68c404czzfff7lg3w"))))
464 (build-system gnu-build-system)
465 (synopsis "C/C++ configuration file library")
467 "Libconfig is a simple library for manipulating structured configuration
468 files. This file format is more compact and more readable than XML. And
469 unlike XML, it is type-aware, so it is not necessary to do string parsing in
471 (license license:lgpl2.1+)))
480 (url "https://github.com/pfff/pfff")
481 (commit (string-append "v" version))))
482 (file-name (git-file-name name version))
485 "1nxkfm7zliq3rmr7yp871sppwfnz71iz364m2sgazny71pzykggc"))))
486 (build-system cmake-build-system)
487 (home-page "https://biit.cs.ut.ee/pfff/")
488 (synopsis "Probabilistic fast file fingerprinting tool")
490 "pfff is a tool for calculating a compact digital fingerprint of a file
491 by sampling randomly from the file instead of reading it in full.
492 Consequently, the computation has a flat performance characteristic,
493 correlated with data variation rather than file size. pfff can be as reliable
494 as existing hashing techniques, with provably negligible risk of collisions.")
495 (license license:bsd-3)))
497 (define-public oniguruma
500 (version "6.9.5-rev1")
503 (uri (string-append "https://github.com/kkos/"
504 "oniguruma/releases/download/v"
505 ;; If there is a "-" in the version, convert
506 ;; to underscore for this part of the URI.
507 (string-map (lambda (c) (if (char=? #\- c) #\_ c))
509 "/onig-" version ".tar.gz"))
512 "17m92k1n6bvza6m35fpd5g36zwpwm3hfz3478iwj5bvj2sfq8g6k"))))
513 (build-system gnu-build-system)
514 (arguments '(#:configure-flags '("--disable-static")))
515 (home-page "https://github.com/kkos/oniguruma")
516 (synopsis "Regular expression library")
517 (description "Oniguruma is a regular expressions library. The special
518 characteristic of this library is that different character encoding for every
519 regular expression object can be specified.")
520 (license license:bsd-2)))
522 (define-public antiword
528 (uri (string-append "http://www.winfield.demon.nl/linux"
529 "/antiword-" version ".tar.gz"))
532 "1b7mi1l20jhj09kyh0bq14qzz8vdhhyf35gzwsq43mn6rc7h0b4f"))
533 (patches (search-patches "antiword-CVE-2014-8123.patch"))))
534 (build-system gnu-build-system)
536 `(#:tests? #f ; There are no tests
538 (list "-f" "Makefile.Linux"
539 (string-append "GLOBAL_INSTALL_DIR="
540 (assoc-ref %outputs "out") "/bin")
541 (string-append "GLOBAL_RESOURCES_DIR="
542 (assoc-ref %outputs "out") "/share/antiword"))
544 (modify-phases %standard-phases
546 (lambda* (#:key outputs #:allow-other-keys)
547 ;; Ensure that mapping files can be found in the actual package
549 (substitute* "antiword.h"
550 (("/usr/share/antiword")
551 (string-append (assoc-ref outputs "out") "/share/antiword")))
554 (lambda* (#:key make-flags #:allow-other-keys)
555 (apply invoke "make" `("global_install" ,@make-flags)))))))
556 (home-page "http://www.winfield.demon.nl/")
557 (synopsis "Microsoft Word document reader")
558 (description "Antiword is an application for displaying Microsoft Word
559 documents. It can also convert the document to PostScript or XML. Only
560 documents made by MS Word version 2 and version 6 or later are supported. The
561 name comes from: \"The antidote against people who send Microsoft Word files
562 to everybody, because they believe that everybody runs Windows and therefore
564 (license license:gpl2+)))
566 (define-public catdoc
572 (uri (string-append "http://ftp.wagner.pp.ru/pub/catdoc/"
573 "catdoc-" version ".tar.gz"))
574 (patches (search-patches "catdoc-CVE-2017-11110.patch"))
577 "15h7v3bmwfk4z8r78xs5ih6vd0pskn0rj90xghvbzdjj0cc88jji"))))
578 (build-system gnu-build-system)
579 ;; TODO: Also build `wordview` which requires `tk` – make a separate
582 '(#:tests? #f ; There are no tests
583 #:configure-flags '("--disable-wordview")
585 (modify-phases %standard-phases
586 (add-before 'install 'fix-install
587 (lambda* (#:key outputs #:allow-other-keys)
588 (let ((out (assoc-ref outputs "out")))
589 (mkdir-p (string-append out "/share/man/man1"))))))))
590 (home-page "https://www.wagner.pp.ru/~vitus/software/catdoc/")
591 (synopsis "MS-Word to TeX or plain text converter")
592 (description "@command{catdoc} extracts text from MS-Word files, trying to
593 preserve as many special printable characters as possible. It supports
594 everything up to Word-97. Also supported are MS Write documents and RTF files.
596 @command{catdoc} does not preserve complex word formatting, but it can
597 translate some non-ASCII characters into TeX escape codes. It's goal is to
598 extract plain text and allow you to read it and, probably, reformat with TeX,
599 according to TeXnical rules.
601 This package also provides @command{xls2csv}, which extracts data from Excel
602 spreadsheets and outputs it in comma-separated-value format, and
603 @command{catppt}, which extracts data from PowerPoint presentations.")
604 (license license:gpl2+)))
606 (define-public utfcpp
613 (url "https://github.com/nemtrif/utfcpp")
614 (commit (string-append "v" version))))
615 (file-name (git-file-name name version))
618 "1gr98d826z6wa58r1s5i7rz7q2x3r31v7zj0pjjlrc7gfxwklr4s"))))
619 (build-system cmake-build-system)
621 `(#:out-of-source? #f
623 (modify-phases %standard-phases
624 (replace 'install ; no install target
625 (lambda* (#:key outputs #:allow-other-keys)
626 (let* ((out (assoc-ref outputs "out"))
627 (include (string-append out "/include"))
628 (doc (string-append out "/share/doc/" ,name)))
629 (copy-recursively "source" include)
630 (install-file "README.md" doc)
632 (home-page "https://github.com/nemtrif/utfcpp")
633 (synopsis "Portable C++ library for handling UTF-8")
634 (description "UTF8-CPP is a C++ library for handling UTF-8 encoded text
636 (license license:boost1.0)))
645 (uri (string-append "mirror://sourceforge/dbacl/dbacl/" version "/"
646 "dbacl-" version ".tar.gz"))
648 (base32 "1gas0112wqjvwn9qg3hxnawk7h3prr0w9b2h68f3p1ifd1kzn3gz"))
649 (patches (search-patches "dbacl-include-locale.h.patch"))))
650 (build-system gnu-build-system)
654 (string-append "-I" (assoc-ref %build-inputs "slang")
656 (string-append "-I" (assoc-ref %build-inputs "ncurses")
659 (modify-phases %standard-phases
660 (add-after 'unpack 'delete-sample6-and-japanese
662 (substitute* "doc/Makefile.am"
664 (("japanese.txt") ""))
665 (delete-file "doc/sample6.txt")
666 (delete-file "doc/japanese.txt")
667 (substitute* (list "src/tests/Makefile.am"
668 "src/tests/Makefile.in")
669 (("dbacl-jap.shin") "")
670 (("dbacl-jap.sh") ""))
672 (add-after 'unpack 'delete-test
673 ;; See comments about the license.
675 (delete-file "src/tests/dbacl-jap.shin")
677 (add-after 'unpack 'fix-test-files
678 (lambda* (#:key inputs outputs #:allow-other-keys)
679 (let* ((out (assoc-ref outputs "out"))
680 (bin (string-append out "/bin")))
681 (substitute* (find-files "src/tests/" "\\.shin$")
682 (("PATH=/bin:/usr/bin")
683 "#PATH=/bin:/usr/bin")
684 (("diff") (string-append (which "diff")))
685 (("tr") (string-append (which "tr"))))
689 (invoke "autoreconf" "-vif")
692 `(("ncurses" ,ncurses)
694 ("readline" ,readline)
697 `(("libtool" ,libtool)
698 ("autoconf" ,autoconf)
699 ("automake" ,automake)
700 ("pkg-config" ,pkg-config)))
701 (home-page "https://www.lbreyer.com/dbacl.html")
702 (synopsis "Bayesian text and email classifier")
704 "dbacl is a fast Bayesian text and email classifier. It builds a variety
705 of language models using maximum entropy (minimum divergence) principles, and
706 these can then be used to categorize input data automatically among multiple
708 ;; The software is licensed as GPLv3 or later, but
709 ;; includes various sample texts in the doc dir:
710 ;; - sample1.txt, sample3 and sampe5.txt are in the public domain,
712 ;; - sample2.txt, sample4.txt are in the public domain, by Aristotle.
713 ;; - sample6.txt is a forwarded email, copyright unknown.
714 ;; Guix does exclude sample6.txt.
715 ;; - japanese.txt is a Japanese unoffical translation of the
716 ;; GNU General Public License, (c) by the Free Software Foundation.
717 ;; Guix excludes this file.
718 (license (list license:gpl3+ license:public-domain))))
720 (define-public dotconf
727 (url "https://github.com/williamh/dotconf")
728 (commit (string-append "v" version))))
729 (file-name (git-file-name name version))
732 "1sc95hw5k2xagpafny0v35filmcn05k1ds5ghkldfpf6xw4hakp7"))))
733 (build-system gnu-build-system)
734 (arguments `(#:tests? #f)) ; FIXME maketest.sh does not work.
736 `(("autoconf" ,autoconf)
737 ("automake" ,automake)
738 ("libtool" ,libtool)))
739 (home-page "https://github.com/williamh/dotconf")
740 (synopsis "Configuration file parser library")
742 "C library for creating and parsing configuration files.")
743 (license (list license:lgpl2.1 ; Main distribution.
744 license:asl1.1)))) ; src/readdir.{c,h}
746 (define-public drm-tools
752 (uri (string-append "mirror://sourceforge/drmtools/drm_tools-"
756 "187zbxw21zcg8gpyc13gxlycfw0n05a6rmqq6im5wr9zk1v1wj80"))))
757 (build-system cmake-build-system)
759 `(#:tests? #f ;the test suite fails
760 #:phases (modify-phases %standard-phases
761 (add-after 'unpack 'set-install-prefixes
762 (lambda* (#:key outputs #:allow-other-keys)
763 (let* ((out (assoc-ref outputs "out")))
764 (substitute* "CMakeLists.txt"
770 (add-after 'unpack 'adjust-test-paths
772 (substitute* '("test_extract_increment.sh"
773 "test_extract_features.sh"
774 "test_extract_features2.sh"
776 (("\\./extract") "extract")
777 (("\\./dmath") "dmath")
778 (("/usr/local/bin/") "")
783 ;; The produced binaries are written directly to %output/bin.
785 (add-after 'build 'check
786 (lambda* (#:key outputs tests? #:allow-other-keys)
788 (let* ((out (assoc-ref outputs "out"))
789 (bin (string-append out "/bin")))
790 (setenv "PATH" (string-append bin ":"
792 (with-directory-excursion
793 (format #f "../drm_tools-~a" ,version)
794 (invoke "sh" "test_all.sh")))))))))
795 (native-inputs `(("which" ,which))) ;for tests
796 (inputs `(("pcre" ,pcre)))
797 (home-page "http://drmtools.sourceforge.net/")
798 (synopsis "Utilities to manipulate text and binary files")
799 (description "The drm_tools package contains the following commands:
802 An extended version of the \"date\" program that has sub-second accuracy.
804 Format complex binary data into text.
806 Load data into a binary file using simple commands from the input.
808 Sort, merge, search, retrieve or generate test data consisting of fixed size
811 Find or find/replace in binary files.
813 Split test data consisting of fixed size binary records into one or more
816 Find changes between two files at the character level. Unlike \"diff\", it
817 lists just the characters that differ, so if the 40,000th character is
818 different only that one character will be shown, not the entire line.
820 Add columns of integers, decimals, and/or times.
822 A utility for formatting binary data dumps.
824 Double precision interactive command line math calculator.
826 Extract and emit data from text files based on character or token position.
828 A utility that reads from STDIN and executes each line as a command in a
831 A utility for rapid retrieval of text by line numbers, in any order, from a
836 Create message queues and send/receive messages.
839 Multiple buffer in and out. Used for buffering a lot of data between a slow
840 device and a fast device. Mostly for buffering streaming tape drives for use
841 with slower network connections, so that streaming is maintained as much as
842 possible to minimize wear on the tape device.
844 Corrupt data streams - useful for testing error correction and data recovery.
846 Filter, list, or split a tar file.
848 (license license:gpl2+)))
850 (define-public java-rsyntaxtextarea
852 (name "java-rsyntaxtextarea")
857 (url "https://github.com/bobbylight/RSyntaxTextArea")
859 (file-name (git-file-name name version))
862 "0dyflzvxq2wvs0rgqfyi5yzzrb6r4bzw2dm8cl304dakxk38ddys"))))
863 (build-system ant-build-system)
865 `(;; FIXME: some tests fail because locale resources cannot be found.
866 ;; Even when I add them to the class path,
867 ;; RSyntaxTextAreaEditorKitDumbCompleteWordActionTest fails.
869 #:jar-name "rsyntaxtextarea.jar"))
871 `(("java-junit" ,java-junit)
872 ("java-hamcrest-core" ,java-hamcrest-core)))
873 (home-page "https://bobbylight.github.io/RSyntaxTextArea/")
874 (synopsis "Syntax highlighting text component for Java Swing")
875 (description "RSyntaxTextArea is a syntax highlighting, code folding text
876 component for Java Swing. It extends @code{JTextComponent} so it integrates
877 completely with the standard @code{javax.swing.text} package. It is fast and
878 efficient, and can be used in any application that needs to edit or view
880 (license license:bsd-3)))
882 ;; We use the sources from git instead of the tarball from pypi, because the
883 ;; latter does not include the Cython source file from which bycython.cpp is
885 (define-public python-editdistance
886 (let ((commit "3ea84a7dd3258c76aa3be851ef3d50e59c886846")
889 (name "python-editdistance")
890 (version (string-append "0.3.1-" revision "." (string-take commit 7)))
895 (url "https://github.com/aflc/editdistance")
897 (file-name (git-file-name name version))
900 "1l43svsv12crvzphrgi6x435z6xg8m086c64armp8wzb4l8ccm7g"))))
901 (build-system python-build-system)
904 (modify-phases %standard-phases
905 (add-after 'unpack 'build-cython-code
907 (with-directory-excursion "editdistance"
908 (delete-file "bycython.cpp")
909 (invoke "cython" "--cplus" "bycython.pyx")))))))
911 `(("python-cython" ,python-cython)))
912 (home-page "https://www.github.com/aflc/editdistance")
913 (synopsis "Fast implementation of the edit distance (Levenshtein distance)")
915 "This library simply implements Levenshtein distance algorithm with C++
917 (license license:expat))))
919 (define-public go-github.com-mattn-go-runewidth
920 (let ((commit "703b5e6b11ae25aeb2af9ebb5d5fdf8fa2575211")
924 (name "go-github.com-mattn-go-runewidth")
925 (version (git-version version revision commit))
930 (url "https://github.com/mattn/runewidth")
932 (file-name (git-file-name name version))
935 "0znpyz71gajx3g0j2zp63nhjj2c07g16885vxv4ykwnrfmzbgk4w"))))
936 (build-system go-build-system)
938 '(#:import-path "github.com/mattn/go-runewidth"))
939 (synopsis "@code{runewidth} provides Go functions to work with string widths")
941 "The @code{runewidth} library provides Go functions for padding,
942 measuring and checking the width of strings, with support for East Asian
944 (home-page "https://github.com/mattn/runewidth")
945 (license license:expat))))
947 (define-public docx2txt
954 "mirror://sourceforge/docx2txt/docx2txt/v"
955 version "/docx2txt-" version ".tgz"))
958 "06vdikjvpj6qdb41d8wzfnyj44jpnknmlgbhbr1w215420lpb5xj"))))
959 (build-system gnu-build-system)
964 `(#:tests? #f ; No tests.
965 #:make-flags (list (string-append "BINDIR="
966 (assoc-ref %outputs "out") "/bin")
967 (string-append "CONFIGDIR="
968 (assoc-ref %outputs "out") "/etc")
969 ;; Makefile seems to be a bit dumb at guessing.
970 (string-append "INSTALL=install")
971 (string-append "PERL=perl"))
973 (modify-phases %standard-phases
975 (add-after 'install 'fix-install
976 (lambda* (#:key outputs inputs #:allow-other-keys)
977 (let* ((out (assoc-ref outputs "out"))
978 (bin (string-append out "/bin"))
979 (config (string-append out "/etc/docx2txt.config"))
980 (unzip (assoc-ref inputs "unzip")))
981 ;; According to INSTALL, the .sh wrapper can be skipped.
982 (delete-file (string-append bin "/docx2txt.sh"))
983 (rename-file (string-append bin "/docx2txt.pl")
984 (string-append bin "/docx2txt"))
986 (("config_unzip => '/usr/bin/unzip',")
987 (string-append "config_unzip => '"
990 ;; Makefile is wrong.
993 (synopsis "Recover text from @file{.docx} files, with good formatting")
995 "@command{docx2txt} is a Perl based command line utility to convert
996 Microsoft Office @file{.docx} documents to equivalent text documents. Latest
997 version supports following features during text extraction.
1000 @item Character conversions; currency characters are converted to respective
1002 @item Capitalisation of text blocks.
1003 @item Center and right justification of text fitting in a line of
1004 (configurable) 80 columns.
1005 @item Horizontal ruler, line breaks, paragraphs separation, tabs.
1006 @item Indicating hyperlinked text along with the hyperlink (configurable).
1007 @item Handling (bullet, decimal, letter, roman) lists along with (attempt at)
1010 (home-page "http://docx2txt.sourceforge.net")
1011 (license license:gpl3+)))
1013 (define-public odt2txt
1021 (url "https://github.com/dstosberg/odt2txt/")
1022 (commit (string-append "v" version))))
1023 (file-name (git-file-name name version))
1026 "0im3kzvhxkjlx57w6h13mc9584c74ma1dyymgvpq2y61av3gc35v"))))
1027 (build-system gnu-build-system)
1029 `(#:tests? #f ; no make check
1030 #:make-flags (list "CC=gcc"
1031 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
1033 (modify-phases %standard-phases
1034 ;; no configure script
1035 (delete 'configure))))
1038 (home-page "https://github.com/dstosberg/odt2txt/")
1039 (synopsis "Converter from OpenDocument Text to plain text")
1040 (description "odt2txt is a command-line tool which extracts the text out
1041 of OpenDocument Texts, as produced by OpenOffice.org, KOffice, StarOffice and
1044 odt2txt can also extract text from some file formats similar to OpenDocument
1045 Text, such as OpenOffice.org XML (*.sxw), which was used by OpenOffice.org
1046 version 1.x and older StarOffice versions. To a lesser extent, odt2txt may be
1047 useful to extract content from OpenDocument spreadsheets (*.ods) and
1048 OpenDocument presentations (*.odp).")
1049 (license license:gpl2)))
1051 (define-public opencc
1059 (url "https://github.com/BYVoid/OpenCC")
1060 (commit (string-append "ver." version))))
1061 (file-name (git-file-name name version))
1064 "1pv5md225qwhbn8ql932zdg6gh1qlx3paiajaks8gfsa07yzvhr4"))
1065 (modules '((guix build utils)))
1068 ;; TODO: Unbundle tclap, darts-clone, gtest
1069 (delete-file-recursively "deps/rapidjson-0.11") #t))))
1070 (build-system cmake-build-system)
1073 (modify-phases %standard-phases
1074 (add-after 'unpack 'patch-3rd-party-references
1075 (lambda* (#:key inputs #:allow-other-keys)
1076 (let ((rapidjson (assoc-ref inputs "rapidjson")))
1077 (substitute* "src/CMakeLists.txt"
1078 (("../deps/rapidjson-0.11")
1079 (string-append rapidjson "/include/rapidjson")))
1082 `(("python" ,python-wrapper)
1083 ("rapidjson" ,rapidjson)))
1084 (home-page "https://github.com/BYVoid/OpenCC")
1085 (synopsis "Convert between Traditional Chinese and Simplified Chinese")
1086 (description "Open Chinese Convert (OpenCC) converts between Traditional
1087 Chinese and Simplified Chinese, supporting character-level conversion,
1088 phrase-level conversion, variant conversion, and regional idioms among
1089 Mainland China, Taiwan, and Hong-Kong.")
1090 (license license:asl2.0)))
1093 (let ((commit "08043eadf4abdddcf277842217e3c77a24740dc2")
1097 ;; The commits corresponding to specific versions are published
1099 ;; https://ja.osdn.net/projects/nkf/scm/git/nkf/
1104 (url "https://github.com/nurse/nkf")
1106 (file-name (git-file-name name version))
1109 "0anw0knr1iy4p9w3d3b3pbwzh1c43p1i2q4c28kw9zviw8kx2rly"))))
1110 (build-system gnu-build-system)
1112 `(#:tests? #f ; test for perl module
1113 #:make-flags (list "CC=gcc" "CFLAGS=-O2 -Wall -pedantic"
1114 (string-append "prefix=" %output)
1117 (modify-phases %standard-phases
1118 (delete 'configure)))) ; No ./configure script
1119 (home-page "https://ja.osdn.net/projects/nkf/")
1120 (synopsis "Network Kanji Filter")
1121 (description "Nkf is yet another kanji code converter among networks,
1122 hosts and terminals. It converts input kanji code to designated kanji code
1123 such as ISO-2022-JP, Shift_JIS, EUC-JP, UTF-8, UTF-16 or UTF-32.")
1124 (license license:zlib))))
1126 (define-public python-pandocfilters
1128 (name "python-pandocfilters")
1133 (uri (pypi-uri "pandocfilters" version))
1136 "1a8d9b7s48gmq9zj0pmbyv2sivn5i7m6mybgpkk4jm5vd7hp1pdk"))))
1137 (build-system python-build-system)
1138 (home-page "https://github.com/jgm/pandocfilters")
1139 (synopsis "Python module for writing Pandoc filters")
1140 (description "Pandoc is a powerful utility to transform various
1141 input formats into a wide range of output formats. To alter the
1142 exported output document, Pandoc allows the usage of filters, which
1143 are pipes that read a JSON serialization of the Pandoc AST from stdin,
1144 transform it in some way, and write it to stdout. It allows therefore
1145 to alter the processing of Pandoc's supported input formats, for
1146 instance one can add new syntax elements to markdown, etc.
1148 This package provides Python bindings.")
1149 (license license:bsd-3)))
1159 (url "https://github.com/theZiz/aha")
1162 (base32 "1gywad0rvvz3c5balz8cxsnx0562hj2ngzqyr8zsy2mb4pn0lpgv"))
1163 (file-name (git-file-name name version))))
1164 (build-system gnu-build-system)
1167 (modify-phases %standard-phases
1168 (delete 'configure))
1169 #:make-flags (list (string-append "CC=" ,(cc-for-target))
1170 (string-append "PREFIX="
1171 (assoc-ref %outputs "out")))
1172 #:tests? #f)) ; no test suite
1173 (home-page "https://github.com/theZiz/aha")
1174 (synopsis "Converts terminal escape sequences to HTML")
1175 (description "@command{aha} (Ansi Html Adapter) converts ANSI escape sequences
1176 of a Unix terminal to HTML code.")
1177 (license (list license:lgpl2.0+ license:mpl1.1))))
1179 (define-public go-github-com-errata-ai-vale
1181 (name "go-github-com-errata-ai-vale")
1187 (url "https://github.com/errata-ai/vale")
1188 (commit (string-append "v" version))))
1190 (base32 "0d07fwha2220m8j24h527xl0gnl3svvyaywflgk5292d6g49ach2"))
1191 (file-name (git-file-name name version))))
1192 (build-system go-build-system)
1194 `(("github.com/sp13/afero" ,go-github-com-spf13-afero)
1195 ("github.com/urfave/cli" ,go-github-com-urfave-cli)
1196 ("github.com/olekukonko/tablewriter" ,go-github-com-olekukonko-tablewriter)
1197 ("github.com/mitchellh/mapstructure" ,go-github-com-mitchellh-mapstructure)))
1199 `(#:import-path "github.com/errata-ai/vale"
1200 #:install-source? #f))
1201 (home-page "https://github.com/errata-ai/vale")
1202 (synopsis "Fully customizable syntax-aware linter that focuses on your style")
1204 "Vale is a fully extensible linter that focuses on your own writing style
1205 by making use of rules in individual YAML files. It is syntax-aware on markup
1206 languages such as HTML, Markdown, Asciidoc, and reStructuredText. The community
1207 around it also has a list of style guides implemented with Vale in
1208 @url{https://github.com/errata-ai/styles, their styles repo}.")
1209 (license license:expat)))