From 618563f0d3b972b9b9075da7e928ca8451a49e77 Mon Sep 17 00:00:00 2001 From: Antoine Brodin Date: Sat, 23 Aug 2014 08:16:57 +0000 Subject: [PATCH] New port: textproc/py-acora Acora is 'fgrep' for Python, a fast multi-keyword text search engine. Based on a set of keywords, it generates a search automaton (DFA) and runs it over string input, either unicode or bytes. It is based on the Aho-Corasick algorithm and an NFA-to-DFA powerset construction. Acora comes with both a pure Python implementation and a fast binary module written in Cython. However, note that the current construction algorithm is not suitable for really large sets of keywords (i.e. more than a couple of thousand). WWW: https://github.com/scoder/acora/ --- textproc/Makefile | 1 + textproc/py-acora/Makefile | 19 +++++++++++++++++++ textproc/py-acora/distinfo | 2 ++ textproc/py-acora/pkg-descr | 9 +++++++++ 4 files changed, 31 insertions(+) create mode 100644 textproc/py-acora/Makefile create mode 100644 textproc/py-acora/distinfo create mode 100644 textproc/py-acora/pkg-descr diff --git a/textproc/Makefile b/textproc/Makefile index 0d021011f754..61c008681597 100644 --- a/textproc/Makefile +++ b/textproc/Makefile @@ -1141,6 +1141,7 @@ SUBDIR += py-Chameleon SUBDIR += py-MarkupSafe SUBDIR += py-Tempita + SUBDIR += py-acora SUBDIR += py-asciinema SUBDIR += py-asv SUBDIR += py-bugzillatools diff --git a/textproc/py-acora/Makefile b/textproc/py-acora/Makefile new file mode 100644 index 000000000000..1aa8127a10ec --- /dev/null +++ b/textproc/py-acora/Makefile @@ -0,0 +1,19 @@ +# Created by: antoine@FreeBSD.org +# $FreeBSD$ + +PORTNAME= acora +PORTVERSION= 1.8 +CATEGORIES= textproc devel python +MASTER_SITES= CHEESESHOP +PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX} + +MAINTAINER= antoine@FreeBSD.org +COMMENT= Fast multi-keyword search engine for text strings + +LICENSE= BSD3CLAUSE +LICENSE_FILE= ${WRKSRC}/LICENSE.txt + +USES= python +USE_PYTHON= distutils autoplist + +.include diff --git a/textproc/py-acora/distinfo b/textproc/py-acora/distinfo new file mode 100644 index 000000000000..559d95639125 --- /dev/null +++ b/textproc/py-acora/distinfo @@ -0,0 +1,2 @@ +SHA256 (acora-1.8.tar.gz) = cfabfbccc31762ae54d05119331051c99837e77e1204c38b9d142f0375c6725b +SIZE (acora-1.8.tar.gz) = 123811 diff --git a/textproc/py-acora/pkg-descr b/textproc/py-acora/pkg-descr new file mode 100644 index 000000000000..886bfef9b3a3 --- /dev/null +++ b/textproc/py-acora/pkg-descr @@ -0,0 +1,9 @@ +Acora is 'fgrep' for Python, a fast multi-keyword text search engine. +Based on a set of keywords, it generates a search automaton (DFA) and runs it +over string input, either unicode or bytes. It is based on the Aho-Corasick +algorithm and an NFA-to-DFA powerset construction. Acora comes with both a pure +Python implementation and a fast binary module written in Cython. However, note +that the current construction algorithm is not suitable for really large sets of +keywords (i.e. more than a couple of thousand). + +WWW: https://github.com/scoder/acora/