1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2015 Taylan Ulrich Bayırlı/Kammer <taylanbayirli@gmail.com>
3 ;;; Copyright © 2015, 2016, 2017 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 Efraim Flashner <efraim@flashner.co.il>
9 ;;; Copyright © 2016 ng0 <ng0@we.make.ritual.n0.is>
10 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
11 ;;; Copyright © 2017 Eric Bavier <bavier@member.fsf.org>
12 ;;; Copyright © 2017 Rene Saavedra <rennes@openmailbox.org>
13 ;;; Copyright © 2017 Hartmut Goebel <h.goebel@crazy-compilers.com>
14 ;;; Copyright © 2017 Kei Kebreau <kkebreau@posteo.net>
15 ;;; Copyright © 2017 Alex Vong <alexvong1995@gmail.com>
17 ;;; This file is part of GNU Guix.
19 ;;; GNU Guix is free software; you can redistribute it and/or modify it
20 ;;; under the terms of the GNU General Public License as published by
21 ;;; the Free Software Foundation; either version 3 of the License, or (at
22 ;;; your option) any later version.
24 ;;; GNU Guix is distributed in the hope that it will be useful, but
25 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;;; GNU General Public License for more details.
29 ;;; You should have received a copy of the GNU General Public License
30 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
32 (define-module (gnu packages textutils)
33 #:use-module ((guix licenses) #:prefix license:)
34 #:use-module (guix packages)
35 #:use-module (guix download)
36 #:use-module (guix git-download)
37 #:use-module (guix build-system ant)
38 #:use-module (guix build-system gnu)
39 #:use-module (guix build-system cmake)
40 #:use-module (guix build-system trivial)
41 #:use-module (gnu packages)
42 #:use-module (gnu packages autotools)
43 #:use-module (gnu packages compression)
44 #:use-module (gnu packages gettext)
45 #:use-module (gnu packages java)
46 #:use-module (gnu packages ncurses)
47 #:use-module (gnu packages perl)
48 #:use-module (gnu packages pkg-config)
49 #:use-module (gnu packages python)
50 #:use-module (gnu packages readline)
51 #:use-module (gnu packages slang))
53 (define-public dos2unix
60 (uri (string-append "https://waterlan.home.xs4all.nl/" name "/"
61 name "-" version ".tar.gz"))
63 (base32 "1i9hbxn0br7xa18z4bjpkdv7mrzmbfxhm44mzpd07yd2qnxsgkcc"))))
64 (build-system gnu-build-system)
66 '(#:make-flags (list "CC=gcc"
67 (string-append "prefix=" (assoc-ref %outputs "out")))
69 (modify-phases %standard-phases
70 (delete 'configure)))) ; no configure script
72 `(("gettext" ,gettext-minimal)
74 (home-page "https://waterlan.home.xs4all.nl/dos2unix.html")
75 (synopsis "DOS/Mac to Unix and vice versa text file format converter")
77 "dos2unix is a tool to convert line breaks in a text file from Unix format
78 to DOS format and vice versa.")
79 (license license:bsd-2)))
84 ;; Last beta release (3.7-beta2) is from 2008; last commit from Feb 2014.
85 ;; So we use that commit instead.
86 (version "3.7.0.201402")
91 (url "https://github.com/pinard/Recode.git")
92 (commit "2d7092a9999194fc0e9449717a8048c8d8e26c18")))
94 (base32 "1wssv8z6g3ryrw33sksz4rjhlnhgvvdqszw1ggl4rcwks34n86zm"))
95 (file-name (string-append name "-" version "-checkout"))))
96 (build-system gnu-build-system)
97 (native-inputs `(("python" ,python-2)))
100 (modify-phases %standard-phases
101 (add-before 'check 'pre-check
103 (substitute* "tests/setup.py"
104 (("([[:space:]]*)include_dirs=.*" all space)
105 (string-append all space "library_dirs=['../src/.libs'],\n")))
106 ;; The test extension 'Recode.so' lacks RUNPATH for 'librecode.so'.
107 (setenv "LD_LIBRARY_PATH" (string-append (getcwd) "/src/.libs"))
109 (home-page "https://github.com/pinard/Recode")
110 (synopsis "Text encoding converter")
111 (description "The Recode library converts files between character sets and
112 usages. It recognises or produces over 200 different character sets (or about
113 300 if combined with an iconv library) and transliterates files between almost
114 any pair. When exact transliteration are not possible, it gets rid of
115 offending characters or falls back on approximations. The recode program is a
116 handy front-end to the library.")
117 (license license:gpl2+)))
127 "https://github.com/nijel/enca/archive/" version ".tar.gz"))
129 (base32 "1xik00x0yvhswsw2isnclabhv536xk1s42cf5z54gfbpbhc7ni8l"))
130 (file-name (string-append name "-" version ".tar.gz"))))
131 (build-system gnu-build-system)
132 (inputs `(("recode" ,recode)))
134 ;; Both 'test-convert-64.sh' and 'test-convert-filter.sh' manipulate a
135 ;; 'test.tmp' file, so they have to run in sequence.
136 (arguments '(#:parallel-tests? #f))
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 "https://github.com/JuliaLang/utf8proc/archive/v"
155 (file-name (string-append name "-" version ".tar.gz"))
157 (base32 "0q1jhdkk4f9b0zb8s2ql3sba3br5nvjsmbsaybmgj064k9hwbk15"))))
158 (build-system gnu-build-system)
159 (inputs ;test data that is otherwise downloaded with curl
160 `(("NormalizationTest.txt"
163 (uri (string-append "http://www.unicode.org/Public/9.0.0/ucd/"
164 "NormalizationTest.txt"))
166 (base32 "1fxrz0bilsbwl685336aqi88k62i6nqhm62rvy4zhg3bcm4dhj1d"))))
167 ("GraphemeBreakTest.txt"
170 (uri (string-append "http://www.unicode.org/Public/9.0.0/ucd/"
171 "auxiliary/GraphemeBreakTest.txt"))
173 (base32 "0qbhyhmf0778lc2hcwlpizrvmdxwpk959v2q2wb8abv09ba7wvn7"))))))
175 '(#:make-flags (list "CC=gcc"
176 (string-append "prefix=" (assoc-ref %outputs "out")))
178 (modify-phases %standard-phases
180 (add-before 'check 'check-data
181 (lambda* (#:key inputs #:allow-other-keys)
182 (for-each (lambda (i)
183 (copy-file (assoc-ref inputs i)
184 (string-append "data/" i)))
185 '("NormalizationTest.txt" "GraphemeBreakTest.txt"))
186 (substitute* "data/GraphemeBreakTest.txt"
189 (home-page "http://julialang.org/utf8proc/")
190 (synopsis "C library for processing UTF-8 Unicode data")
191 (description "utf8proc is a small C library that provides Unicode
192 normalization, case-folding, and other operations for data in the UTF-8
193 encoding, supporting Unicode version 9.0.0.")
194 (license license:expat)))
196 (define-public libgtextutils
198 (name "libgtextutils")
204 "https://github.com/agordon/libgtextutils/releases/download/"
205 version "/libgtextutils-" version ".tar.gz"))
207 (base32 "0jiybkb2z58wa2msvllnphr4js2hvjvh988pavb3mzkgr6ihwbkr"))))
208 (build-system gnu-build-system)
211 (modify-phases %standard-phases
212 (add-after 'unpack 'autoreconf
213 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
215 `(("autoconf" ,autoconf)
216 ("automake" ,automake)
217 ("libtool" ,libtool)))
218 (home-page "https://github.com/agordon/libgtextutils")
219 (synopsis "Gordon's text utils library")
221 "libgtextutils is a text utilities library used by the fastx toolkit from
223 (license license:agpl3+)))
225 (define-public cityhash
226 (let ((commit "8af9b8c"))
229 (version (string-append "1.1-2." commit))
233 (url "https://github.com/google/cityhash.git")
235 (file-name (string-append name "-" version ".tar.gz"))
238 "0n6skf5dv8yfl1ckax8dqhvsbslkwc9158zf2ims0xqdvzsahbi6"))))
239 (build-system gnu-build-system)
241 '(#:make-flags (list "CXXFLAGS=-g -O3")
243 (modify-phases %standard-phases
244 ;; citycrc is not installed by default but is used by some
246 (add-after 'install 'install-citycrc
247 (lambda* (#:key outputs #:allow-other-keys)
248 (let* ((out (assoc-ref outputs "out"))
249 (include (string-append out "/include")))
250 (install-file "src/citycrc.h" include))
252 (home-page "https://github.com/google/cityhash")
253 (synopsis "C++ hash functions for strings")
255 "CityHash provides hash functions for strings. The functions mix the
256 input bits thoroughly but are not suitable for cryptography.")
257 (license license:expat))))
265 (uri (string-append "http://www.and.org/ustr/" version
266 "/ustr-" version ".tar.bz2"))
269 "1i623ygdj7rkizj7985q9d6vj5amwg686aqb5j3ixpkqkyp6xbrx"))
270 (patches (search-patches "ustr-fix-build-with-gcc-5.patch"))))
271 (build-system gnu-build-system)
276 ;; Override "/sbin/ldconfig" with "echo" because we don't need
279 (string-append "prefix=" (assoc-ref %outputs "out"))
282 (modify-phases %standard-phases
283 (add-after 'unpack 'disable-check-for-stdint
285 ;; Of course we have stdint.h, just not in /usr/include
286 (substitute* '("Makefile"
288 (("-f \"/usr/include/stdint.h\"") "-z \"\""))
290 ;; No configure script
291 (delete 'configure))))
292 (home-page "http://www.and.org/ustr/")
293 (synopsis "String library with very low memory overhead")
295 "Ustr is a string library for C with very low memory overhead.")
296 ;; Quoted from the home page: "The License for the code is MIT, new-BSD,
297 ;; LGPL, etc. ... if you need another license to help compatibility, just
298 ;; ask for it. It's basically public domain, without all the legal
299 ;; problems for everyone that trying to make something public domain
301 (license license:public-domain)))
303 (define-public libconfig
309 (uri (string-append "http://www.hyperrealm.com/libconfig/"
310 "libconfig-" version ".tar.gz"))
313 "1xh3hzk63v4y8815lc5209m3s6ms2cpgw4h5hg462i4f1lwsl7g3"))))
314 (build-system gnu-build-system)
315 (home-page "http://www.hyperrealm.com/libconfig/")
316 (synopsis "C/C++ configuration file library")
318 "Libconfig is a simple library for manipulating structured configuration
319 files. This file format is more compact and more readable than XML. And
320 unlike XML, it is type-aware, so it is not necessary to do string parsing in
322 (license license:lgpl2.1+)))
330 (uri (string-append "https://github.com/pfff/pfff/archive/v"
332 (file-name (string-append name "-" version ".tar.gz"))
335 "00m553aa277iarxj6dalmklyb64r7ias49bfwzbacsfg8h3kar8m"))))
336 (build-system cmake-build-system)
337 (home-page "http://biit.cs.ut.ee/pfff/")
338 (synopsis "Probabilistic fast file fingerprinting tool")
340 "pfff is a tool for calculating a compact digital fingerprint of a file
341 by sampling randomly from the file instead of reading it in full.
342 Consequently, the computation has a flat performance characteristic,
343 correlated with data variation rather than file size. pfff can be as reliable
344 as existing hashing techniques, with provably negligible risk of collisions.")
345 (license license:bsd-3)))
347 (define-public oniguruma
353 (uri (string-append "https://github.com/kkos/"
354 "oniguruma/releases/download/v" version
355 "/onig-" version ".tar.gz"))
358 "19s79vsclqn170mw0ajwv7j37qsbn4f1yjz3yavnhvva6c820r6m"))))
359 (build-system gnu-build-system)
360 (home-page "https://github.com/kkos/oniguruma")
361 (synopsis "Regular expression library")
362 (description "Oniguruma is a regular expressions library. The special
363 characteristic of this library is that different character encoding for every
364 regular expression object can be specified.")
365 (license license:bsd-2)))
367 (define-public antiword
373 (uri (string-append "http://www.winfield.demon.nl/linux"
374 "/antiword-" version ".tar.gz"))
377 "1b7mi1l20jhj09kyh0bq14qzz8vdhhyf35gzwsq43mn6rc7h0b4f"))
378 (patches (search-patches "antiword-CVE-2014-8123.patch"))))
379 (build-system gnu-build-system)
381 `(#:tests? #f ; There are no tests
383 (list "-f" "Makefile.Linux"
384 (string-append "GLOBAL_INSTALL_DIR="
385 (assoc-ref %outputs "out") "/bin")
386 (string-append "GLOBAL_RESOURCES_DIR="
387 (assoc-ref %outputs "out") "/share/antiword"))
389 (modify-phases %standard-phases
392 (lambda* (#:key make-flags #:allow-other-keys)
393 (zero? (apply system* "make" `("global_install" ,@make-flags))))))))
394 (home-page "http://www.winfield.demon.nl/")
395 (synopsis "Microsoft Word document reader")
396 (description "Antiword is an application for displaying Microsoft Word
397 documents. It can also convert the document to PostScript or XML. Only
398 documents made by MS Word version 2 and version 6 or later are supported. The
399 name comes from: \"The antidote against people who send Microsoft Word files
400 to everybody, because they believe that everybody runs Windows and therefore
402 (license license:gpl2+)))
404 (define-public catdoc
410 (uri (string-append "http://ftp.wagner.pp.ru/pub/catdoc/"
411 "catdoc-" version ".tar.gz"))
412 (patches (search-patches "catdoc-CVE-2017-11110.patch"))
415 "15h7v3bmwfk4z8r78xs5ih6vd0pskn0rj90xghvbzdjj0cc88jji"))))
416 (build-system gnu-build-system)
417 ;; TODO: Also build `wordview` which requires `tk` – make a separate
420 '(#:tests? #f ; There are no tests
421 #:configure-flags '("--disable-wordview")
423 (modify-phases %standard-phases
424 (add-before 'install 'fix-install
425 (lambda* (#:key outputs #:allow-other-keys)
426 (let ((out (assoc-ref outputs "out")))
427 (mkdir-p (string-append out "/share/man/man1"))))))))
428 (home-page "http://www.wagner.pp.ru/~vitus/software/catdoc/")
429 (synopsis "MS-Word to TeX or plain text converter")
430 (description "@command{catdoc} extracts text from MS-Word files, trying to
431 preserve as many special printable characters as possible. It supports
432 everything up to Word-97. Also supported are MS Write documents and RTF files.
434 @command{catdoc} does not preserve complex word formatting, but it can
435 translate some non-ASCII characters into TeX escape codes. It's goal is to
436 extract plain text and allow you to read it and, probably, reformat with TeX,
437 according to TeXnical rules.
439 This package also provides @command{xls2csv}, which extracts data from Excel
440 spreadsheets and outputs it in comma-separated-value format, and
441 @command{catppt}, which extracts data from PowerPoint presentations.")
442 (license license:gpl2+)))
444 (define-public utfcpp
452 "mirror://sourceforge/utfcpp/utf8cpp_2x/Release%20"
454 (string-map (lambda (x) (if (eq? x #\.) #\_ x)) version)
456 (file-name (string-append name "-" version ".zip"))
459 "1vqhs0aipcvvdrwcs7h3jsryg6mgbmc4s34n5cm6d36q4nxwwwrk"))))
460 (build-system trivial-build-system)
462 `(#:modules ((guix build utils))
465 (use-modules (guix build utils))
466 (let ((source (assoc-ref %build-inputs "source"))
467 (out (assoc-ref %outputs "out"))
468 (unzip (string-append (assoc-ref %build-inputs "unzip")
471 (with-directory-excursion out
472 (system* unzip source)
473 (mkdir-p "share/doc")
474 (rename-file "doc" "share/doc/utfcpp")
475 (rename-file "source" "include"))))))
476 (native-inputs `(("unzip" ,unzip)))
477 (home-page "https://github.com/nemtrif/utfcpp")
478 (synopsis "Portable C++ library for handling UTF-8")
479 (description "UTF8-CPP is a C++ library for handling UTF-8 encoded text
481 (license license:boost1.0)))
490 (uri (string-append "http://www.lbreyer.com/gpl/"
491 name "-" version ".tar.gz"))
494 "0224g6x71hyvy7jikfxmgcwww1r5lvk0jx36cva319cb9nmrbrq7"))))
495 (build-system gnu-build-system)
499 (string-append "-I" (assoc-ref %build-inputs "slang")
501 (string-append "-I" (assoc-ref %build-inputs "ncurses")
504 (modify-phases %standard-phases
505 (add-after 'unpack 'delete-sample6-and-japanese
507 (substitute* "doc/Makefile.am"
509 (("japanese.txt") ""))
510 (delete-file "doc/sample6.txt")
511 (delete-file "doc/japanese.txt")
512 (substitute* (list "src/tests/Makefile.am"
513 "src/tests/Makefile.in")
514 (("dbacl-jap.shin") "")
515 (("dbacl-jap.sh") ""))
517 (add-after 'unpack 'delete-test
518 ;; See comments about the license.
520 (delete-file "src/tests/dbacl-jap.shin")))
521 (add-after 'delete-sample6-and-japanese 'autoreconf
523 (zero? (system* "autoreconf" "-vif"))))
524 (add-after 'unpack 'fix-test-files
525 (lambda* (#:key inputs outputs #:allow-other-keys)
526 (let* ((out (assoc-ref outputs "out"))
527 (bin (string-append out "/bin")))
528 (substitute* (find-files "src/tests/" "\\.shin$")
529 (("PATH=/bin:/usr/bin")
530 "#PATH=/bin:/usr/bin")
531 (("diff") (string-append (which "diff")))
532 (("tr") (string-append (which "tr"))))
535 `(("ncurses" ,ncurses)
537 ("readline" ,readline)
540 `(("libtool" ,libtool)
541 ("autoconf" ,autoconf)
542 ("automake" ,automake)
543 ("pkg-config" ,pkg-config)))
544 (home-page "http://www.lbreyer.com/dbacl.html")
545 (synopsis "Bayesian text and email classifier")
547 "dbacl is a fast Bayesian text and email classifier. It builds a variety
548 of language models using maximum entropy (minimum divergence) principles, and
549 these can then be used to categorize input data automatically among multiple
551 ;; The software is licensed as GPLv3 or later, but
552 ;; includes various sample texts in the doc dir:
553 ;; - sample1.txt, sample3 and sampe5.txt are in the public domain,
555 ;; - sample2.txt, sample4.txt are in the public domain, by Aristotle.
556 ;; - sample6.txt is a forwarded email, copyright unknown.
557 ;; Guix does exclude sample6.txt.
558 ;; - japanese.txt is a Japanese unoffical translation of the
559 ;; GNU General Public License, (c) by the Free Software Foundation.
560 ;; Guix excludes this file.
561 (license (list license:gpl3+ license:public-domain))))
563 (define-public dotconf
570 "https://github.com/williamh/dotconf/archive/v"
572 (file-name (string-append name "-" version ".tar.gz"))
575 "0lsnh0yaw44psmx59hq94cj1932gscp5h8d3cnh05l0svr0cy7kz"))))
576 (build-system gnu-build-system)
578 `(#:tests? #f ; FIXME maketest.sh does not work.
580 (modify-phases %standard-phases
581 (add-after 'unpack 'autoreconf
583 (zero? (system* "autoreconf" "-vif")))))))
585 `(("autoconf" ,autoconf)
586 ("automake" ,automake)
587 ("libtool" ,libtool)))
588 (home-page "https://github.com/williamh/dotconf")
589 (synopsis "Configuration file parser library")
591 "C library for creating and parsing configuration files.")
592 (license (list license:lgpl2.1 ; Main distribution.
593 license:asl1.1)))) ; src/readdir.{c,h}
595 (define-public java-rsyntaxtextarea
597 (name "java-rsyntaxtextarea")
601 (uri (string-append "https://github.com/bobbylight/"
602 "RSyntaxTextArea/archive/"
604 (file-name (string-append name "-" version ".tar.gz"))
607 "0c5mqg2klj5rvf8fhycrli8rf6s37l9p7a8knw9gpp65r1c120q2"))))
608 (build-system ant-build-system)
610 `(;; FIXME: some tests fail because locale resources cannot be found.
611 ;; Even when I add them to the class path,
612 ;; RSyntaxTextAreaEditorKitDumbCompleteWordActionTest fails.
614 #:jar-name "rsyntaxtextarea.jar"))
616 `(("java-junit" ,java-junit)
617 ("java-hamcrest-core" ,java-hamcrest-core)))
618 (home-page "https://bobbylight.github.io/RSyntaxTextArea/")
619 (synopsis "Syntax highlighting text component for Java Swing")
620 (description "RSyntaxTextArea is a syntax highlighting, code folding text
621 component for Java Swing. It extends @code{JTextComponent} so it integrates
622 completely with the standard @code{javax.swing.text} package. It is fast and
623 efficient, and can be used in any application that needs to edit or view
625 (license license:bsd-3)))