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 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 gettext)
56 #:use-module (gnu packages java)
57 #:use-module (gnu packages ncurses)
58 #:use-module (gnu packages pcre)
59 #:use-module (gnu packages perl)
60 #:use-module (gnu packages pkg-config)
61 #:use-module (gnu packages python)
62 #:use-module (gnu packages python-xyz)
63 #:use-module (gnu packages readline)
64 #:use-module (gnu packages slang)
65 #:use-module (gnu packages web))
67 (define-public dos2unix
74 (uri (string-append "https://waterlan.home.xs4all.nl/dos2unix/"
75 "dos2unix-" version ".tar.gz"))
77 (base32 "08w6yywzirsxq8bh87jycvvw922ybhc2l426j2iqzliyn1h8mm8w"))))
78 (build-system gnu-build-system)
80 '(#:make-flags (list "CC=gcc"
81 (string-append "prefix=" (assoc-ref %outputs "out")))
83 (modify-phases %standard-phases
84 (delete 'configure)))) ; no configure script
86 `(("gettext" ,gettext-minimal)
88 (home-page "https://waterlan.home.xs4all.nl/dos2unix.html")
89 (synopsis "DOS/Mac to Unix and vice versa text file format converter")
91 "dos2unix is a tool to convert line breaks in a text file from Unix format
92 to DOS format and vice versa.")
93 (license license:bsd-2)))
102 (uri (string-append "https://github.com/rrthomas/recode/releases/"
103 "download/v" version "/recode-" version ".tar.gz"))
105 (base32 "0m59sd1ca0zw1aydpc3m8sw03nc885knmccqryg7byzmqs585ia6"))))
106 (build-system gnu-build-system)
109 ("python-cython" ,python-cython)))
110 (home-page "https://github.com/rrthomas/recode")
111 (synopsis "Text encoding converter")
112 (description "The Recode library converts files between character sets and
113 usages. It recognises or produces over 200 different character sets (or about
114 300 if combined with an iconv library) and transliterates files between almost
115 any pair. When exact transliteration are not possible, it gets rid of
116 offending characters or falls back on approximations. The recode program is a
117 handy front-end to the library.")
118 (license license:gpl3+)))
128 (url "https://github.com/nijel/enca")
130 (file-name (git-file-name name version))
132 (base32 "19q7cwwxmmk5j9438bsqdpjvdjawsd3zmw1zyqgi7s4m0rasr3ah"))))
133 (build-system gnu-build-system)
134 ;; enca-1.19 tests fail with recent recode.
135 ;(inputs `(("recode" ,recode)))
136 (home-page "https://github.com/nijel/enca")
137 (synopsis "Text encoding detection tool")
138 (description "Enca (Extremely Naive Charset Analyser) consists of libenca,
139 an encoding detection library, and enca, a command line frontend, integrating
140 libenca and several charset conversion libraries and tools.")
141 (license license:gpl2)))
143 (define-public utf8proc
151 (url "https://github.com/JuliaStrings/utf8proc")
152 (commit (string-append "v" version))))
153 (file-name (git-file-name name version))
155 (base32 "1xlkazhdnja4lksn5c9nf4bln5gjqa35a8gwlam5r0728w0h83qq"))))
156 (build-system gnu-build-system)
158 (let ((UNICODE_VERSION "13.0.0")) ; defined in data/Makefile
159 ;; Test data that is otherwise downloaded with curl.
160 `(("NormalizationTest.txt"
163 (uri (string-append "https://www.unicode.org/Public/"
164 UNICODE_VERSION "/ucd/NormalizationTest.txt"))
166 (base32 "07g0ya4f6zfzvpp24ccxkb2yq568kh83gls85rjl950nv5fya3nn"))))
167 ("GraphemeBreakTest.txt"
170 (uri (string-append "https://www.unicode.org/Public/"
172 "/ucd/auxiliary/GraphemeBreakTest.txt"))
174 (base32 "07f8rrvcsq4pibdz6zxggxy8w7zjjqyw2ggclqlhalyv45yv7prj"))))
179 '(#:make-flags (list "CC=gcc"
180 (string-append "prefix=" (assoc-ref %outputs "out")))
182 (modify-phases %standard-phases
184 (add-before 'check 'check-data
185 (lambda* (#:key inputs #:allow-other-keys)
186 (for-each (lambda (i)
187 (copy-file (assoc-ref inputs i)
188 (string-append "data/" i)))
189 '("NormalizationTest.txt" "GraphemeBreakTest.txt"))
190 (substitute* "data/GraphemeBreakTest.txt"
194 (home-page "https://juliastrings.github.io/utf8proc/")
195 (synopsis "C library for processing UTF-8 Unicode data")
196 (description "utf8proc is a small C library that provides Unicode
197 normalization, case-folding, and other operations for data in the UTF-8
198 encoding, supporting Unicode version 9.0.0.")
199 (license license:expat)))
201 (define-public libconfuse
208 (uri (string-append "https://github.com/martinh/libconfuse/"
209 "releases/download/v" version
210 "/confuse-" version ".tar.xz"))
212 (base32 "043hqqykpprgrkw9s2hbdlxr308a7yxwsgxj4m8aadg1401hmm8x"))))
213 (build-system gnu-build-system)
215 '(#:configure-flags '("--disable-static")))
216 (home-page "https://github.com/martinh/libconfuse")
217 (synopsis "Configuration file parser library")
218 (description "libconfuse is a configuration file parser library. It
219 supports sections and (lists of) values (strings, integers, floats, booleans
220 or other sections), as well as some other features (such as
221 single/double-quoted strings, environment variable expansion, functions and
222 nested include statements).")
223 (license license:isc)))
225 (define-public libgtextutils
227 (name "libgtextutils")
233 "https://github.com/agordon/libgtextutils/releases/download/"
234 version "/libgtextutils-" version ".tar.gz"))
236 (base32 "0jiybkb2z58wa2msvllnphr4js2hvjvh988pavb3mzkgr6ihwbkr"))))
237 (build-system gnu-build-system)
240 (modify-phases %standard-phases
242 (lambda _ (invoke "sh" "reconf")))
243 (add-after 'set-paths 'hide-default-gcc
244 (lambda* (#:key inputs #:allow-other-keys)
245 (let ((gcc (assoc-ref inputs "gcc")))
246 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
247 ;; conflicts with the GCC 5 input.
248 (setenv "CPLUS_INCLUDE_PATH"
250 (delete (string-append gcc "/include/c++")
251 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
255 `(("autoconf" ,autoconf)
256 ("automake" ,automake)
257 ("gcc@5" ,gcc-5) ; doesn't build with later versions
258 ("libtool" ,libtool)))
259 (home-page "https://github.com/agordon/libgtextutils")
260 (synopsis "Gordon's text utils library")
262 "libgtextutils is a text utilities library used by the fastx toolkit from
264 (license license:agpl3+)))
266 (define-public cityhash
267 (let ((commit "8af9b8c"))
270 (version (string-append "1.1-2." commit))
274 (url "https://github.com/google/cityhash")
276 (file-name (string-append name "-" version ".tar.gz"))
279 "0n6skf5dv8yfl1ckax8dqhvsbslkwc9158zf2ims0xqdvzsahbi6"))))
280 (build-system gnu-build-system)
282 '(#:make-flags (list "CXXFLAGS=-g -O3")
284 (modify-phases %standard-phases
285 ;; citycrc is not installed by default but is used by some
287 (add-after 'install 'install-citycrc
288 (lambda* (#:key outputs #:allow-other-keys)
289 (let* ((out (assoc-ref outputs "out"))
290 (include (string-append out "/include")))
291 (install-file "src/citycrc.h" include))
293 (home-page "https://github.com/google/cityhash")
294 (synopsis "C++ hash functions for strings")
296 "CityHash provides hash functions for strings. The functions mix the
297 input bits thoroughly but are not suitable for cryptography.")
298 (license license:expat))))
306 (uri (string-append "http://www.and.org/ustr/" version
307 "/ustr-" version ".tar.bz2"))
310 "1i623ygdj7rkizj7985q9d6vj5amwg686aqb5j3ixpkqkyp6xbrx"))
311 (patches (search-patches "ustr-fix-build-with-gcc-5.patch"))))
312 (build-system gnu-build-system)
317 ;; Override "/sbin/ldconfig" with "echo" because we don't need
320 (string-append "prefix=" (assoc-ref %outputs "out"))
323 (modify-phases %standard-phases
324 (add-after 'unpack 'disable-check-for-stdint
326 ;; Of course we have stdint.h, just not in /usr/include
327 (substitute* '("Makefile"
329 (("-f \"/usr/include/stdint.h\"") "-z \"\""))
331 ;; No configure script
332 (delete 'configure))))
333 (home-page "http://www.and.org/ustr/")
334 (synopsis "String library with very low memory overhead")
336 "Ustr is a string library for C with very low memory overhead.")
337 ;; Quoted from the home page: "The License for the code is MIT, new-BSD,
338 ;; LGPL, etc. ... if you need another license to help compatibility, just
339 ;; ask for it. It's basically public domain, without all the legal
340 ;; problems for everyone that trying to make something public domain
342 (license license:public-domain)))
344 (define-public ascii2binary
346 (name "ascii2binary")
351 (uri (string-append "http://billposer.org/Software/Downloads/"
352 "ascii2binary-" version ".tar.bz2"))
354 (base32 "0dc9fxcdmppbs9s06jvq61zbk552laxps0xyk098gj41697ihd96"))))
355 (build-system gnu-build-system)
357 `(("gettext" ,gettext-minimal)))
358 (home-page "https://billposer.org/Software/a2b.html")
359 (synopsis "Convert between ASCII, hexadecimal and binary representations")
360 (description "The two programs are useful for generating test data, for
361 inspecting binary files, and for interfacing programs that generate textual
362 output to programs that require binary input and conversely. They can also be
363 useful when it is desired to reformat numbers.
367 @item @command{ascii2binary} reads input consisting of ascii or hexadecimal
368 representation numbers separated by whitespace and produces as output
369 the binary equivalents. The type and precision of the binary output
370 is selected using command line flags.
372 @item @command{binary2ascii} reads input consisting of binary numbers
373 and converts them to their ascii or hexadecimal representation.
374 Command line flags specify the type and size of the binary numbers
375 and provide control over the format of the output.
376 Unsigned integers may be written out in binary, octal, decimal,
379 Signed integers may be written out only in binary or decimal. Floating
380 point numbers may be written out only decimal, either in standard or
381 scientific notation. (If you want to examine the binary representation
382 of floating point numbers, just treat the input as a sequence of unsigned
386 (license license:gpl3)))
388 (define-public uniutils
395 (uri (string-append "http://billposer.org/Software/Downloads/"
396 "uniutils-" version ".tar.bz2"))
398 (base32 "19w1510w87gx7n4qy3zsb0m467a4rn5scvh4ajajg7jh6x5xri08"))))
399 (build-system gnu-build-system)
401 '(#:configure-flags '("--disable-dependency-tracking")
403 (modify-phases %standard-phases
404 (add-after 'build 'fix-paths
405 (lambda* (#:key outputs inputs #:allow-other-keys)
406 (let ((out (assoc-ref outputs "out"))
407 (a2b (assoc-ref inputs "ascii2binary"))
408 (iconv (assoc-ref inputs "libiconv")))
409 (substitute* "utf8lookup"
410 (("^ascii2binary ") (string-append a2b "/bin/ascii2binary "))
411 (("^uniname ") (string-append out "/bin/uniname "))
412 (("^iconv ") (string-append iconv "/bin/iconv ")))
415 `(("ascii2binary" ,ascii2binary)
416 ("libiconv" ,libiconv)))
417 (home-page "https://billposer.org/Software/unidesc.html")
418 (synopsis "Find out what is in a Unicode file")
419 (description "Useful tools when working with Unicode files when one
420 doesn't know the writing system, doesn't have the necessary font, needs to
421 inspect invisible characters, needs to find out whether characters have been
422 combined or in what order they occur, or needs statistics on which characters
427 @item @command{uniname} defaults to printing the character offset of each
428 character, its byte offset, its hex code value, its encoding, the glyph
429 itself, and its name. It may also be used to validate UTF-8 input.
431 @item @command{unidesc} reports the character ranges to which different
432 portions of the text belong. It can also be used to identify Unicode encodings
433 (e.g. UTF-16be) flagged by magic numbers.
435 @item @command{unihist} generates a histogram of the characters in its input.
437 @item @command{ExplicateUTF8} is intended for debugging or for learning about
438 Unicode. It determines and explains the validity of a sequence of bytes as a
441 @item @command{utf8lookup} provides a handy way to look up Unicode characters
442 from the command line.
444 @item @command{unireverse} reverse each line of UTF-8 input
445 character-by-character.
448 (license license:gpl3)))
450 (define-public libconfig
454 (home-page "https://hyperrealm.github.io/libconfig/")
457 (uri (string-append home-page "/dist/libconfig-"
461 "1ngs2qx3cx5cbwinc5mvadly0b5n7s86zsc68c404czzfff7lg3w"))))
462 (build-system gnu-build-system)
463 (synopsis "C/C++ configuration file library")
465 "Libconfig is a simple library for manipulating structured configuration
466 files. This file format is more compact and more readable than XML. And
467 unlike XML, it is type-aware, so it is not necessary to do string parsing in
469 (license license:lgpl2.1+)))
478 (url "https://github.com/pfff/pfff")
479 (commit (string-append "v" version))))
480 (file-name (git-file-name name version))
483 "1nxkfm7zliq3rmr7yp871sppwfnz71iz364m2sgazny71pzykggc"))))
484 (build-system cmake-build-system)
485 (home-page "https://biit.cs.ut.ee/pfff/")
486 (synopsis "Probabilistic fast file fingerprinting tool")
488 "pfff is a tool for calculating a compact digital fingerprint of a file
489 by sampling randomly from the file instead of reading it in full.
490 Consequently, the computation has a flat performance characteristic,
491 correlated with data variation rather than file size. pfff can be as reliable
492 as existing hashing techniques, with provably negligible risk of collisions.")
493 (license license:bsd-3)))
495 (define-public oniguruma
498 (version "6.9.5-rev1")
501 (uri (string-append "https://github.com/kkos/"
502 "oniguruma/releases/download/v"
503 ;; If there is a "-" in the version, convert
504 ;; to underscore for this part of the URI.
505 (string-map (lambda (c) (if (char=? #\- c) #\_ c))
507 "/onig-" version ".tar.gz"))
510 "17m92k1n6bvza6m35fpd5g36zwpwm3hfz3478iwj5bvj2sfq8g6k"))))
511 (build-system gnu-build-system)
512 (arguments '(#:configure-flags '("--disable-static")))
513 (home-page "https://github.com/kkos/oniguruma")
514 (synopsis "Regular expression library")
515 (description "Oniguruma is a regular expressions library. The special
516 characteristic of this library is that different character encoding for every
517 regular expression object can be specified.")
518 (license license:bsd-2)))
520 (define-public antiword
526 (uri (string-append "http://www.winfield.demon.nl/linux"
527 "/antiword-" version ".tar.gz"))
530 "1b7mi1l20jhj09kyh0bq14qzz8vdhhyf35gzwsq43mn6rc7h0b4f"))
531 (patches (search-patches "antiword-CVE-2014-8123.patch"))))
532 (build-system gnu-build-system)
534 `(#:tests? #f ; There are no tests
536 (list "-f" "Makefile.Linux"
537 (string-append "GLOBAL_INSTALL_DIR="
538 (assoc-ref %outputs "out") "/bin")
539 (string-append "GLOBAL_RESOURCES_DIR="
540 (assoc-ref %outputs "out") "/share/antiword"))
542 (modify-phases %standard-phases
544 (lambda* (#:key outputs #:allow-other-keys)
545 ;; Ensure that mapping files can be found in the actual package
547 (substitute* "antiword.h"
548 (("/usr/share/antiword")
549 (string-append (assoc-ref outputs "out") "/share/antiword")))
552 (lambda* (#:key make-flags #:allow-other-keys)
553 (apply invoke "make" `("global_install" ,@make-flags)))))))
554 (home-page "http://www.winfield.demon.nl/")
555 (synopsis "Microsoft Word document reader")
556 (description "Antiword is an application for displaying Microsoft Word
557 documents. It can also convert the document to PostScript or XML. Only
558 documents made by MS Word version 2 and version 6 or later are supported. The
559 name comes from: \"The antidote against people who send Microsoft Word files
560 to everybody, because they believe that everybody runs Windows and therefore
562 (license license:gpl2+)))
564 (define-public catdoc
570 (uri (string-append "http://ftp.wagner.pp.ru/pub/catdoc/"
571 "catdoc-" version ".tar.gz"))
572 (patches (search-patches "catdoc-CVE-2017-11110.patch"))
575 "15h7v3bmwfk4z8r78xs5ih6vd0pskn0rj90xghvbzdjj0cc88jji"))))
576 (build-system gnu-build-system)
577 ;; TODO: Also build `wordview` which requires `tk` – make a separate
580 '(#:tests? #f ; There are no tests
581 #:configure-flags '("--disable-wordview")
583 (modify-phases %standard-phases
584 (add-before 'install 'fix-install
585 (lambda* (#:key outputs #:allow-other-keys)
586 (let ((out (assoc-ref outputs "out")))
587 (mkdir-p (string-append out "/share/man/man1"))))))))
588 (home-page "https://www.wagner.pp.ru/~vitus/software/catdoc/")
589 (synopsis "MS-Word to TeX or plain text converter")
590 (description "@command{catdoc} extracts text from MS-Word files, trying to
591 preserve as many special printable characters as possible. It supports
592 everything up to Word-97. Also supported are MS Write documents and RTF files.
594 @command{catdoc} does not preserve complex word formatting, but it can
595 translate some non-ASCII characters into TeX escape codes. It's goal is to
596 extract plain text and allow you to read it and, probably, reformat with TeX,
597 according to TeXnical rules.
599 This package also provides @command{xls2csv}, which extracts data from Excel
600 spreadsheets and outputs it in comma-separated-value format, and
601 @command{catppt}, which extracts data from PowerPoint presentations.")
602 (license license:gpl2+)))
604 (define-public utfcpp
611 (url "https://github.com/nemtrif/utfcpp")
612 (commit (string-append "v" version))))
613 (file-name (git-file-name name version))
616 "1gr98d826z6wa58r1s5i7rz7q2x3r31v7zj0pjjlrc7gfxwklr4s"))))
617 (build-system cmake-build-system)
619 `(#:out-of-source? #f
621 (modify-phases %standard-phases
622 (replace 'install ; no install target
623 (lambda* (#:key outputs #:allow-other-keys)
624 (let* ((out (assoc-ref outputs "out"))
625 (include (string-append out "/include"))
626 (doc (string-append out "/share/doc/" ,name)))
627 (copy-recursively "source" include)
628 (install-file "README.md" doc)
630 (home-page "https://github.com/nemtrif/utfcpp")
631 (synopsis "Portable C++ library for handling UTF-8")
632 (description "UTF8-CPP is a C++ library for handling UTF-8 encoded text
634 (license license:boost1.0)))
643 (uri (string-append "mirror://sourceforge/dbacl/dbacl/" version "/"
644 "dbacl-" version ".tar.gz"))
646 (base32 "1gas0112wqjvwn9qg3hxnawk7h3prr0w9b2h68f3p1ifd1kzn3gz"))
647 (patches (search-patches "dbacl-include-locale.h.patch"))))
648 (build-system gnu-build-system)
652 (string-append "-I" (assoc-ref %build-inputs "slang")
654 (string-append "-I" (assoc-ref %build-inputs "ncurses")
657 (modify-phases %standard-phases
658 (add-after 'unpack 'delete-sample6-and-japanese
660 (substitute* "doc/Makefile.am"
662 (("japanese.txt") ""))
663 (delete-file "doc/sample6.txt")
664 (delete-file "doc/japanese.txt")
665 (substitute* (list "src/tests/Makefile.am"
666 "src/tests/Makefile.in")
667 (("dbacl-jap.shin") "")
668 (("dbacl-jap.sh") ""))
670 (add-after 'unpack 'delete-test
671 ;; See comments about the license.
673 (delete-file "src/tests/dbacl-jap.shin")
675 (add-after 'unpack 'fix-test-files
676 (lambda* (#:key inputs outputs #:allow-other-keys)
677 (let* ((out (assoc-ref outputs "out"))
678 (bin (string-append out "/bin")))
679 (substitute* (find-files "src/tests/" "\\.shin$")
680 (("PATH=/bin:/usr/bin")
681 "#PATH=/bin:/usr/bin")
682 (("diff") (string-append (which "diff")))
683 (("tr") (string-append (which "tr"))))
687 (invoke "autoreconf" "-vif")
690 `(("ncurses" ,ncurses)
692 ("readline" ,readline)
695 `(("libtool" ,libtool)
696 ("autoconf" ,autoconf)
697 ("automake" ,automake)
698 ("pkg-config" ,pkg-config)))
699 (home-page "https://www.lbreyer.com/dbacl.html")
700 (synopsis "Bayesian text and email classifier")
702 "dbacl is a fast Bayesian text and email classifier. It builds a variety
703 of language models using maximum entropy (minimum divergence) principles, and
704 these can then be used to categorize input data automatically among multiple
706 ;; The software is licensed as GPLv3 or later, but
707 ;; includes various sample texts in the doc dir:
708 ;; - sample1.txt, sample3 and sampe5.txt are in the public domain,
710 ;; - sample2.txt, sample4.txt are in the public domain, by Aristotle.
711 ;; - sample6.txt is a forwarded email, copyright unknown.
712 ;; Guix does exclude sample6.txt.
713 ;; - japanese.txt is a Japanese unoffical translation of the
714 ;; GNU General Public License, (c) by the Free Software Foundation.
715 ;; Guix excludes this file.
716 (license (list license:gpl3+ license:public-domain))))
718 (define-public dotconf
725 (url "https://github.com/williamh/dotconf")
726 (commit (string-append "v" version))))
727 (file-name (git-file-name name version))
730 "1sc95hw5k2xagpafny0v35filmcn05k1ds5ghkldfpf6xw4hakp7"))))
731 (build-system gnu-build-system)
732 (arguments `(#:tests? #f)) ; FIXME maketest.sh does not work.
734 `(("autoconf" ,autoconf)
735 ("automake" ,automake)
736 ("libtool" ,libtool)))
737 (home-page "https://github.com/williamh/dotconf")
738 (synopsis "Configuration file parser library")
740 "C library for creating and parsing configuration files.")
741 (license (list license:lgpl2.1 ; Main distribution.
742 license:asl1.1)))) ; src/readdir.{c,h}
744 (define-public drm-tools
750 (uri (string-append "mirror://sourceforge/drmtools/drm_tools-"
754 "187zbxw21zcg8gpyc13gxlycfw0n05a6rmqq6im5wr9zk1v1wj80"))))
755 (build-system cmake-build-system)
757 `(#:tests? #f ;the test suite fails
758 #:phases (modify-phases %standard-phases
759 (add-after 'unpack 'set-install-prefixes
760 (lambda* (#:key outputs #:allow-other-keys)
761 (let* ((out (assoc-ref outputs "out")))
762 (substitute* "CMakeLists.txt"
768 (add-after 'unpack 'adjust-test-paths
770 (substitute* '("test_extract_increment.sh"
771 "test_extract_features.sh"
772 "test_extract_features2.sh"
774 (("\\./extract") "extract")
775 (("\\./dmath") "dmath")
776 (("/usr/local/bin/") "")
781 ;; The produced binaries are written directly to %output/bin.
783 (add-after 'build 'check
784 (lambda* (#:key outputs tests? #:allow-other-keys)
786 (let* ((out (assoc-ref outputs "out"))
787 (bin (string-append out "/bin")))
788 (setenv "PATH" (string-append bin ":"
790 (with-directory-excursion
791 (format #f "../drm_tools-~a" ,version)
792 (invoke "sh" "test_all.sh")))))))))
793 (native-inputs `(("which" ,which))) ;for tests
794 (inputs `(("pcre" ,pcre)))
795 (home-page "http://drmtools.sourceforge.net/")
796 (synopsis "Utilities to manipulate text and binary files")
797 (description "The drm_tools package contains the following commands:
800 An extended version of the \"date\" program that has sub-second accuracy.
802 Format complex binary data into text.
804 Load data into a binary file using simple commands from the input.
806 Sort, merge, search, retrieve or generate test data consisting of fixed size
809 Find or find/replace in binary files.
811 Split test data consisting of fixed size binary records into one or more
814 Find changes between two files at the character level. Unlike \"diff\", it
815 lists just the characters that differ, so if the 40,000th character is
816 different only that one character will be shown, not the entire line.
818 Add columns of integers, decimals, and/or times.
820 A utility for formatting binary data dumps.
822 Double precision interactive command line math calculator.
824 Extract and emit data from text files based on character or token position.
826 A utility that reads from STDIN and executes each line as a command in a
829 A utility for rapid retrieval of text by line numbers, in any order, from a
834 Create message queues and send/receive messages.
837 Multiple buffer in and out. Used for buffering a lot of data between a slow
838 device and a fast device. Mostly for buffering streaming tape drives for use
839 with slower network connections, so that streaming is maintained as much as
840 possible to minimize wear on the tape device.
842 Corrupt data streams - useful for testing error correction and data recovery.
844 Filter, list, or split a tar file.
846 (license license:gpl2+)))
848 (define-public java-rsyntaxtextarea
850 (name "java-rsyntaxtextarea")
854 (uri (string-append "https://github.com/bobbylight/"
855 "RSyntaxTextArea/archive/"
857 (file-name (string-append name "-" version ".tar.gz"))
860 "0c5mqg2klj5rvf8fhycrli8rf6s37l9p7a8knw9gpp65r1c120q2"))))
861 (build-system ant-build-system)
863 `(;; FIXME: some tests fail because locale resources cannot be found.
864 ;; Even when I add them to the class path,
865 ;; RSyntaxTextAreaEditorKitDumbCompleteWordActionTest fails.
867 #:jar-name "rsyntaxtextarea.jar"))
869 `(("java-junit" ,java-junit)
870 ("java-hamcrest-core" ,java-hamcrest-core)))
871 (home-page "https://bobbylight.github.io/RSyntaxTextArea/")
872 (synopsis "Syntax highlighting text component for Java Swing")
873 (description "RSyntaxTextArea is a syntax highlighting, code folding text
874 component for Java Swing. It extends @code{JTextComponent} so it integrates
875 completely with the standard @code{javax.swing.text} package. It is fast and
876 efficient, and can be used in any application that needs to edit or view
878 (license license:bsd-3)))
880 ;; We use the sources from git instead of the tarball from pypi, because the
881 ;; latter does not include the Cython source file from which bycython.cpp is
883 (define-public python-editdistance
884 (let ((commit "3ea84a7dd3258c76aa3be851ef3d50e59c886846")
887 (name "python-editdistance")
888 (version (string-append "0.3.1-" revision "." (string-take commit 7)))
893 (url "https://github.com/aflc/editdistance")
895 (file-name (git-file-name name version))
898 "1l43svsv12crvzphrgi6x435z6xg8m086c64armp8wzb4l8ccm7g"))))
899 (build-system python-build-system)
902 (modify-phases %standard-phases
903 (add-after 'unpack 'build-cython-code
905 (with-directory-excursion "editdistance"
906 (delete-file "bycython.cpp")
907 (invoke "cython" "--cplus" "bycython.pyx")))))))
909 `(("python-cython" ,python-cython)))
910 (home-page "https://www.github.com/aflc/editdistance")
911 (synopsis "Fast implementation of the edit distance (Levenshtein distance)")
913 "This library simply implements Levenshtein distance algorithm with C++
915 (license license:expat))))
917 (define-public go-github.com-mattn-go-runewidth
918 (let ((commit "703b5e6b11ae25aeb2af9ebb5d5fdf8fa2575211")
922 (name "go-github.com-mattn-go-runewidth")
923 (version (git-version version revision commit))
928 (url "https://github.com/mattn/runewidth")
930 (file-name (git-file-name name version))
933 "0znpyz71gajx3g0j2zp63nhjj2c07g16885vxv4ykwnrfmzbgk4w"))))
934 (build-system go-build-system)
936 '(#:import-path "github.com/mattn/go-runewidth"))
937 (synopsis "@code{runewidth} provides Go functions to work with string widths")
939 "The @code{runewidth} library provides Go functions for padding,
940 measuring and checking the width of strings, with support for East Asian
942 (home-page "https://github.com/mattn/runewidth")
943 (license license:expat))))
945 (define-public docx2txt
952 "mirror://sourceforge/docx2txt/docx2txt/v"
953 version "/docx2txt-" version ".tgz"))
956 "06vdikjvpj6qdb41d8wzfnyj44jpnknmlgbhbr1w215420lpb5xj"))))
957 (build-system gnu-build-system)
962 `(#:tests? #f ; No tests.
963 #:make-flags (list (string-append "BINDIR="
964 (assoc-ref %outputs "out") "/bin")
965 (string-append "CONFIGDIR="
966 (assoc-ref %outputs "out") "/etc")
967 ;; Makefile seems to be a bit dumb at guessing.
968 (string-append "INSTALL=install")
969 (string-append "PERL=perl"))
971 (modify-phases %standard-phases
973 (add-after 'install 'fix-install
974 (lambda* (#:key outputs inputs #:allow-other-keys)
975 (let* ((out (assoc-ref outputs "out"))
976 (bin (string-append out "/bin"))
977 (config (string-append out "/etc/docx2txt.config"))
978 (unzip (assoc-ref inputs "unzip")))
979 ;; According to INSTALL, the .sh wrapper can be skipped.
980 (delete-file (string-append bin "/docx2txt.sh"))
981 (rename-file (string-append bin "/docx2txt.pl")
982 (string-append bin "/docx2txt"))
984 (("config_unzip => '/usr/bin/unzip',")
985 (string-append "config_unzip => '"
988 ;; Makefile is wrong.
991 (synopsis "Recover text from @file{.docx} files, with good formatting")
993 "@command{docx2txt} is a Perl based command line utility to convert
994 Microsoft Office @file{.docx} documents to equivalent text documents. Latest
995 version supports following features during text extraction.
998 @item Character conversions; currency characters are converted to respective
1000 @item Capitalisation of text blocks.
1001 @item Center and right justification of text fitting in a line of
1002 (configurable) 80 columns.
1003 @item Horizontal ruler, line breaks, paragraphs separation, tabs.
1004 @item Indicating hyperlinked text along with the hyperlink (configurable).
1005 @item Handling (bullet, decimal, letter, roman) lists along with (attempt at)
1008 (home-page "http://docx2txt.sourceforge.net")
1009 (license license:gpl3+)))
1011 (define-public odt2txt
1019 (url "https://github.com/dstosberg/odt2txt/")
1020 (commit (string-append "v" version))))
1021 (file-name (git-file-name name version))
1024 "0im3kzvhxkjlx57w6h13mc9584c74ma1dyymgvpq2y61av3gc35v"))))
1025 (build-system gnu-build-system)
1027 `(#:tests? #f ; no make check
1028 #:make-flags (list "CC=gcc"
1029 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
1031 (modify-phases %standard-phases
1032 ;; no configure script
1033 (delete 'configure))))
1036 (home-page "https://github.com/dstosberg/odt2txt/")
1037 (synopsis "Converter from OpenDocument Text to plain text")
1038 (description "odt2txt is a command-line tool which extracts the text out
1039 of OpenDocument Texts, as produced by OpenOffice.org, KOffice, StarOffice and
1042 odt2txt can also extract text from some file formats similar to OpenDocument
1043 Text, such as OpenOffice.org XML (*.sxw), which was used by OpenOffice.org
1044 version 1.x and older StarOffice versions. To a lesser extent, odt2txt may be
1045 useful to extract content from OpenDocument spreadsheets (*.ods) and
1046 OpenDocument presentations (*.odp).")
1047 (license license:gpl2)))
1049 (define-public opencc
1057 (url "https://github.com/BYVoid/OpenCC")
1058 (commit (string-append "ver." version))))
1059 (file-name (git-file-name name version))
1062 "1pv5md225qwhbn8ql932zdg6gh1qlx3paiajaks8gfsa07yzvhr4"))
1063 (modules '((guix build utils)))
1066 ;; TODO: Unbundle tclap, darts-clone, gtest
1067 (delete-file-recursively "deps/rapidjson-0.11") #t))))
1068 (build-system cmake-build-system)
1071 (modify-phases %standard-phases
1072 (add-after 'unpack 'patch-3rd-party-references
1073 (lambda* (#:key inputs #:allow-other-keys)
1074 (let ((rapidjson (assoc-ref inputs "rapidjson")))
1075 (substitute* "src/CMakeLists.txt"
1076 (("../deps/rapidjson-0.11")
1077 (string-append rapidjson "/include/rapidjson")))
1080 `(("python" ,python-wrapper)
1081 ("rapidjson" ,rapidjson)))
1082 (home-page "https://github.com/BYVoid/OpenCC")
1083 (synopsis "Convert between Traditional Chinese and Simplified Chinese")
1084 (description "Open Chinese Convert (OpenCC) converts between Traditional
1085 Chinese and Simplified Chinese, supporting character-level conversion,
1086 phrase-level conversion, variant conversion, and regional idioms among
1087 Mainland China, Taiwan, and Hong-Kong.")
1088 (license license:asl2.0)))
1091 (let ((commit "08043eadf4abdddcf277842217e3c77a24740dc2")
1095 ;; The commits corresponding to specific versions are published
1097 ;; https://ja.osdn.net/projects/nkf/scm/git/nkf/
1102 (url "https://github.com/nurse/nkf")
1104 (file-name (git-file-name name version))
1107 "0anw0knr1iy4p9w3d3b3pbwzh1c43p1i2q4c28kw9zviw8kx2rly"))))
1108 (build-system gnu-build-system)
1110 `(#:tests? #f ; test for perl module
1111 #:make-flags (list "CC=gcc" "CFLAGS=-O2 -Wall -pedantic"
1112 (string-append "prefix=" %output)
1115 (modify-phases %standard-phases
1116 (delete 'configure)))) ; No ./configure script
1117 (home-page "https://ja.osdn.net/projects/nkf/")
1118 (synopsis "Network Kanji Filter")
1119 (description "Nkf is yet another kanji code converter among networks,
1120 hosts and terminals. It converts input kanji code to designated kanji code
1121 such as ISO-2022-JP, Shift_JIS, EUC-JP, UTF-8, UTF-16 or UTF-32.")
1122 (license license:zlib))))
1124 (define-public python-pandocfilters
1126 (name "python-pandocfilters")
1131 (uri (pypi-uri "pandocfilters" version))
1134 "1a8d9b7s48gmq9zj0pmbyv2sivn5i7m6mybgpkk4jm5vd7hp1pdk"))))
1135 (build-system python-build-system)
1136 (home-page "https://github.com/jgm/pandocfilters")
1137 (synopsis "Python module for writing Pandoc filters")
1138 (description "Pandoc is a powerful utility to transform various
1139 input formats into a wide range of output formats. To alter the
1140 exported output document, Pandoc allows the usage of filters, which
1141 are pipes that read a JSON serialization of the Pandoc AST from stdin,
1142 transform it in some way, and write it to stdout. It allows therefore
1143 to alter the processing of Pandoc's supported input formats, for
1144 instance one can add new syntax elements to markdown, etc.
1146 This package provides Python bindings.")
1147 (license license:bsd-3)))
1157 (url "https://github.com/theZiz/aha")
1160 (base32 "1gywad0rvvz3c5balz8cxsnx0562hj2ngzqyr8zsy2mb4pn0lpgv"))
1161 (file-name (git-file-name name version))))
1162 (build-system gnu-build-system)
1165 (modify-phases %standard-phases
1166 (delete 'configure))
1167 #:make-flags (list (string-append "CC=" ,(cc-for-target))
1168 (string-append "PREFIX="
1169 (assoc-ref %outputs "out")))
1170 #:tests? #f)) ; no test suite
1171 (home-page "https://github.com/theZiz/aha")
1172 (synopsis "Converts terminal escape sequences to HTML")
1173 (description "@command{aha} (Ansi Html Adapter) converts ANSI escape sequences
1174 of a Unix terminal to HTML code.")
1175 (license (list license:lgpl2.0+ license:mpl1.1))))